© 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. 22534
    Prev
    Next
    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    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
    _SYNC
    -0.29
    çļĦéĢŁåº¦
    -0.26
    æī§
    -0.26
    éĢŁ
    -0.26
    åľ¨æĦı
    -0.25
    .transfer
    -0.25
    æľĢå¿«çļĦ
    -0.25
    è¿Ļ件
    -0.24
    _SOL
    -0.24
    RELATED
    -0.24
    POSITIVE LOGITS
     bearings
    0.28
     blank
    0.27
    uar
    0.27
     mess
    0.27
     bearing
    0.25
    mess
    0.25
     black
    0.25
     po
    0.25
    å°ĸ
    0.24
    -desc
    0.24
    Activations Density 0.005%

    No Known Activations