© 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. 30-TRANSCODER-HP
    7. 95526
    Prev
    Next
    INDEX
    Explanations

    Random contexts and languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embar
    -0.27
    åı¦ä¸Ģç§į
    -0.26
     Visibility
    -0.25
     Versions
    -0.24
     !_
    -0.24
     Independent
    -0.24
    ysize
    -0.24
    åIJİèĢħ
    -0.24
    çĭ¬ç«ĭ
    -0.23
     Ec
    -0.23
    POSITIVE LOGITS
    avana
    0.29
    çħİ
    0.27
    unts
    0.27
    ÅĤoż
    0.27
     Lanka
    0.25
     Furn
    0.25
    çĺ¸
    0.25
    åĪ©çİĩ
    0.25
    enez
    0.24
     caster
    0.24
    Activations Density 0.788%

    No Known Activations