© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8892
    Prev
    Next
    INDEX
    Explanations

    proper nouns and capitalization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    麹
    -0.28
    çģ«çĤ¬
    -0.27
    ocities
    -0.24
    infeld
    -0.24
    -off
    -0.24
    AtPath
    -0.24
    éļı
    -0.24
    ught
    -0.23
    .writeValue
    -0.23
    ä¸Ģç·Ĵãģ«
    -0.23
    POSITIVE LOGITS
    erver
    0.28
    ylv
    0.27
     ÑģоÑģÑĤ
    0.27
    æİĮæı¡
    0.26
    udder
    0.26
    ĥģ
    0.25
    oho
    0.25
    oger
    0.25
    ãģ¦ãĤĭ
    0.25
    ITOR
    0.25
    Activations Density 1.010%

    No Known Activations