© 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. 9-TRANSCODER-HP
    7. 29931
    Prev
    Next
    INDEX
    Explanations

    Ag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubar
    -0.33
    sz
    -0.33
    lá
    -0.29
    æĹģ
    -0.29
     threatened
    -0.27
    AFX
    -0.26
    ä½ķæŶ
    -0.26
     Routes
    -0.26
    IÃĵN
    -0.25
    Memcpy
    -0.25
    POSITIVE LOGITS
    crease
    0.26
     beforehand
    0.25
    oul
    0.25
     Between
    0.25
     Fault
    0.25
    Height
    0.25
    existence
    0.24
    ç«¥
    0.24
    ries
    0.24
    ureau
    0.23
    Activations Density 1.040%

    No Known Activations