© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150217
    Prev
    Next
    INDEX
    Explanations

    Code and file-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataMember
    -0.27
    ProcessEvent
    -0.25
    ãģ¾ãģĹãģ¦
    -0.24
    busters
    -0.24
     noticing
    -0.23
    ckill
    -0.23
    ãĥ³ãĥĪ
    -0.23
    ennie
    -0.23
     hereby
    -0.23
    èĬĥ
    -0.22
    POSITIVE LOGITS
    ç°§
    0.28
    èħ¥
    0.26
    **↵↵
    0.26
    **
    0.25
    &m
    0.24
    """↵↵
    0.24
    fe
    0.24
    ****************************************************************
    0.23
    arat
    0.23
    å±İ
    0.23
    Activations Density 2.682%

    No Known Activations