© 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. 54266
    Prev
    Next
    INDEX
    Explanations

    bb

    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
    åĬ¨éĿĻ
    -0.28
    èĢ³
    -0.26
     mo
    -0.26
    lat
    -0.26
    aise
    -0.26
     Ep
    -0.26
    à¹Īà¸ĩ
    -0.25
    fav
    -0.25
     option
    -0.25
    Ep
    -0.25
    POSITIVE LOGITS
    icies
    0.27
    bery
    0.26
     Dummy
    0.25
     Formatter
    0.25
    orary
    0.25
     spilled
    0.25
     Budd
    0.24
    hya
    0.24
    çªĦ
    0.24
    igi
    0.24
    Activations Density 0.003%

    No Known Activations