© 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. 54090
    Prev
    Next
    INDEX
    Explanations

    flea

    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
    iesz
    -0.33
    èĭį
    -0.30
    عÙĬÙĨ
    -0.29
    INET
    -0.28
    aran
    -0.28
    net
    -0.28
    dr
    -0.28
    éĽªå±±
    -0.28
    tmp
    -0.27
    åħ¨çľģ
    -0.26
    POSITIVE LOGITS
     organ
    0.28
    /*@
    0.27
    olls
    0.27
     beet
    0.27
    åĻ¨å®ĺ
    0.26
    ala
    0.26
     saliva
    0.25
    alty
    0.25
     Beet
    0.25
    è¯įæĿ¡
    0.25
    Activations Density 0.021%

    No Known Activations