© 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. 35-TRANSCODER-HP
    7. 39499
    Prev
    Next
    INDEX
    Explanations

    oc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    our
    -0.32
    OUR
    -0.31
    ir
    -0.28
    iv
    -0.27
     Our
    -0.26
    Ir
    -0.26
    åĿļå®Ī
    -0.26
    egen
    -0.25
     present
    -0.25
     OUR
    -0.25
    POSITIVE LOGITS
    ope
    0.31
    urve
    0.30
    ise
    0.30
    APE
    0.30
    ede
    0.28
    ipe
    0.28
    aine
    0.28
    ube
    0.28
    ISE
    0.28
    observ
    0.27
    Activations Density 14.619%

    No Known Activations