© 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. 32-TRANSCODER-HP
    7. 43415
    Prev
    Next
    INDEX
    Explanations

    Bl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ross
    -0.30
    交
    -0.29
    оÑĩек
    -0.27
    CP
    -0.26
     pl
    -0.26
    Ich
    -0.26
    çıĬ
    -0.26
     اÙĦØŃر
    -0.25
    AQ
    -0.25
    NaN
    -0.25
    POSITIVE LOGITS
    emento
    0.29
     Held
    0.27
     held
    0.27
    hung
    0.27
    ¤æĸŃ
    0.26
     Gemini
    0.26
    emony
    0.25
    ELY
    0.25
    ç»ĪæŃ¢
    0.25
     hole
    0.24
    Activations Density 0.004%

    No Known Activations