© 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. 31-TRANSCODER-HP
    7. 19731
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿Ļæĺ¯ä¸Ģç§į
    -0.27
    ä»ĺè´¹
    -0.27
    ·»
    -0.27
    æį¨ãģ¦
    -0.25
    ict
    -0.24
    éľľ
    -0.23
    /*------------------------------------------------
    -0.23
     called
    -0.23
    иÑĩеÑģкÑĥÑİ
    -0.23
     confines
    -0.23
    POSITIVE LOGITS
     having
    0.53
     Having
    0.44
     that
    0.43
    having
    0.43
    Having
    0.42
     avoir
    0.33
     rằng
    0.31
     have
    0.30
     being
    0.30
     for
    0.30
    Activations Density 0.122%

    No Known Activations