© 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. 23945
    Prev
    Next
    INDEX
    Explanations

    refrigerators

    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
     instant
    -0.28
     reflective
    -0.27
     reflected
    -0.27
     settled
    -0.27
    adh
    -0.26
    éļĶçĥŃ
    -0.26
     intrigued
    -0.26
    icare
    -0.25
    ãĥ©ãĥ¼
    -0.25
    éŃħåĬĽ
    -0.25
    POSITIVE LOGITS
     mafia
    0.25
    侪
    0.25
     exceed
    0.25
    è¶ħé«ĺ
    0.25
    åī¯æķĻæİĪ
    0.24
    _virtual
    0.24
    lhs
    0.24
    chemist
    0.24
    cff
    0.24
    tems
    0.24
    Activations Density 0.001%

    No Known Activations