© 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. 23-TRANSCODER-HP
    7. 25421
    Prev
    Next
    INDEX
    Explanations

    Obligation or necessity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¿ħé¡»
    -0.32
    Must
    -0.31
    åıĪè¦ģ
    -0.30
    å¿ħé¡»è¦ģ
    -0.30
     Must
    -0.30
    nor
    -0.30
    è¦ģ
    -0.30
    must
    -0.28
    è¦ģåıĬæŶ
    -0.28
    ä¹Łä¸įåı¯èĥ½
    -0.27
    POSITIVE LOGITS
    ä¸įä»ħèĥ½
    0.28
    ä¸įä»ħåı¯ä»¥
    0.26
    æī¾åĪ°äºĨ
    0.26
    å¾Īæ£Ĵ
    0.26
     seen
    0.25
    ä¸Ģ家
    0.25
    éĿŀ常éĢĤåIJĪ
    0.24
    änd
    0.24
     scrapped
    0.24
     numer
    0.24
    Activations Density 0.026%

    No Known Activations