© 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. 24104
    Prev
    Next
    INDEX
    Explanations

    efficiency

    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
    åĬ©
    -0.26
     anc
    -0.26
     Native
    -0.25
    容
    -0.25
    ượng
    -0.25
    åı°æ¹¾
    -0.25
    (O
    -0.25
    ech
    -0.24
     pratic
    -0.24
    bling
    -0.24
    POSITIVE LOGITS
    éģ¿å¼Ģ
    0.32
    ä¼ļ产çĶŁ
    0.26
     agreeing
    0.25
     waived
    0.25
     tiá»ģm
    0.25
    VA
    0.25
    ptron
    0.24
     SKF
    0.24
    æľŁéĹ´
    0.24
    åĬłå¼ºå¯¹
    0.24
    Activations Density 0.001%

    No Known Activations