© 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. 33-TRANSCODER-HP
    7. 53762
    Prev
    Next
    INDEX
    Explanations

    Code/identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uniform
    -0.36
     verg
    -0.28
    è´¯éĢļ
    -0.27
    èĮħ
    -0.27
    ersonic
    -0.26
    uniform
    -0.26
     Verg
    -0.26
     cot
    -0.25
    ä¸Ńåħ³
    -0.25
     che
    -0.25
    POSITIVE LOGITS
    uron
    0.31
    UGE
    0.31
    hoe
    0.29
    èĩªçĦ¶èĢĮ
    0.28
    urs
    0.27
    tons
    0.26
    ä¸į解
    0.26
    hound
    0.26
    kat
    0.25
    hole
    0.25
    Activations Density 0.004%

    No Known Activations