© 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. 30-TRANSCODER-HP
    7. 96002
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ¼
    -0.29
    è´¨
    -0.27
    èĢĥå¯Ł
    -0.27
     Starr
    -0.27
    ures
    -0.27
    æķĪçİĩ
    -0.26
    iers
    -0.25
    è§Ĩå¯Ł
    -0.24
    gross
    -0.24
     vig
    -0.24
    POSITIVE LOGITS
    èĻŁ
    0.28
    æĽľ
    0.27
    eph
    0.27
    hel
    0.27
    .ali
    0.26
    OI
    0.25
    å¼ĢåѦ
    0.25
     Needle
    0.24
    hf
    0.24
    åı·
    0.24
    Activations Density 0.885%

    No Known Activations