© 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. 53690
    Prev
    Next
    INDEX
    Explanations

    Quotation marks/parenthesis

    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
     GANG
    -0.26
    ément
    -0.26
    MSC
    -0.26
    strain
    -0.26
     finale
    -0.25
    onis
    -0.25
    gist
    -0.25
     pies
    -0.25
    cation
    -0.25
    TERS
    -0.24
    POSITIVE LOGITS
     Pool
    0.31
     Place
    0.31
     City
    0.29
    place
    0.28
    Place
    0.27
    enia
    0.27
    åľ°æĸ¹
    0.27
     Home
    0.27
    Path
    0.27
    _HOME
    0.27
    Activations Density 0.021%

    No Known Activations