© 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. 95294
    Prev
    Next
    INDEX
    Explanations

    large numbers

    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
     covered
    -0.28
     host
    -0.26
    ió
    -0.26
    产çĶŁ
    -0.26
     cover
    -0.25
    OTS
    -0.25
    .dw
    -0.25
     promoted
    -0.25
    WER
    -0.25
    çªĿ
    -0.24
    POSITIVE LOGITS
     Pdf
    0.27
    饮
    0.26
     byteArray
    0.26
    åĬ«
    0.26
    uality
    0.26
    æŁĶæĢ§
    0.26
    jsc
    0.25
     Inject
    0.25
    oles
    0.25
    argent
    0.25
    Activations Density 0.001%

    No Known Activations