© 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. 9-TRANSCODER-HP
    7. 30074
    Prev
    Next
    INDEX
    Explanations

    establishment dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biological
    -0.26
    .lv
    -0.26
     adjective
    -0.24
    ioned
    -0.23
    _CF
    -0.23
    鸳
    -0.22
    .social
    -0.22
    PrototypeOf
    -0.22
    _methods
    -0.22
    ted
    -0.22
    POSITIVE LOGITS
     Affero
    0.26
     `,
    0.25
    海滩
    0.25
    ç²¾åĬĽ
    0.25
    æµ·è¾¹
    0.23
    Unnamed
    0.23
    phanumeric
    0.23
     cloth
    0.23
     `%
    0.23
    unch
    0.23
    Activations Density 7.016%

    No Known Activations