© 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. 12-TRANSCODER-HP
    7. 23403
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨħåľ°
    -0.27
     initState
    -0.26
     ActionType
    -0.26
    big
    -0.25
     controlId
    -0.25
     Constit
    -0.25
    Tiles
    -0.24
     кÑĢед
    -0.24
    å¢ĥåĨħ
    -0.24
    нÑĥÑĤ
    -0.23
    POSITIVE LOGITS
    -access
    0.29
    iesel
    0.26
    ually
    0.26
    uche
    0.26
    ĥģ
    0.26
     determination
    0.25
     accessibility
    0.25
    ups
    0.25
    ssql
    0.24
     sharpen
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.