© 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. 96153
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     trial
    -0.28
    åĵij
    -0.26
    ivre
    -0.26
    erval
    -0.24
    _audit
    -0.24
    æ£ĢéªĮ
    -0.24
     prze
    -0.24
    trial
    -0.24
    éªĮ
    -0.24
    htm
    -0.24
    POSITIVE LOGITS
    иÑĤелÑĮно
    0.28
    åįĹå±±
    0.28
    æĿŀ
    0.27
     bât
    0.27
    aser
    0.27
     Build
    0.26
    builders
    0.26
    itech
    0.25
    build
    0.25
    ÑĢÑĥÑĪ
    0.25
    Activations Density 0.103%

    No Known Activations