© 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. 18-TRANSCODER-HP
    7. 89782
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ance
    -0.29
    umbing
    -0.27
    amiento
    -0.26
    acr
    -0.26
    GridView
    -0.26
    isel
    -0.25
    ergarten
    -0.25
    oidal
    -0.25
    ition
    -0.24
    ances
    -0.24
    POSITIVE LOGITS
     surv
    0.27
    æ¢Ĺ
    0.25
     sur
    0.25
    弯
    0.24
    ä»
    0.24
     cr
    0.24
    尽头
    0.24
     cadre
    0.24
     üst
    0.23
    _JO
    0.23
    Activations Density 4.428%

    No Known Activations