© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23990
    Prev
    Next
    INDEX
    Explanations

    publish

    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
    Negative Logits
    æľ«
    -0.29
    ailable
    -0.28
    å±Ģéĥ¨
    -0.26
    æŁ´
    -0.24
    StateException
    -0.24
     sweep
    -0.24
     manh
    -0.24
     Swe
    -0.24
    Incomplete
    -0.24
    çŃīå¾ħ
    -0.24
    POSITIVE LOGITS
    anke
    0.31
    Blake
    0.28
     Bols
    0.27
     defaulted
    0.26
    伤
    0.26
     StringBuffer
    0.24
    PGA
    0.24
     seznam
    0.24
    注æĺİåĩºå¤Ħ
    0.23
    aptive
    0.23
    Activations Density 0.009%

    No Known Activations