© 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. 25-TRANSCODER-HP
    7. 107121
    Prev
    Next
    INDEX
    Explanations

    formal/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pointers
    -0.28
    é¦Ĺ
    -0.26
    好åIJĹ
    -0.26
    çĨĦ
    -0.25
    abo
    -0.25
    åĵį
    -0.24
    lew
    -0.24
    мÑĭ
    -0.24
     billed
    -0.23
    æĪĺèĥľ
    -0.23
    POSITIVE LOGITS
    ardu
    0.29
     puff
    0.28
    predicate
    0.26
    /people
    0.25
    çĦļçĥ§
    0.25
     VAT
    0.24
    ARDS
    0.24
    çİ«
    0.24
    remen
    0.24
    æī¹åıij
    0.24
    Activations Density 0.101%

    No Known Activations