© 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. 96691
    Prev
    Next
    INDEX
    Explanations

    Uri

    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
     Paw
    -0.26
    .toCharArray
    -0.25
     needed
    -0.24
    ordinated
    -0.24
    Ŷ
    -0.23
    FINE
    -0.23
     basal
    -0.23
    undi
    -0.23
    .xr
    -0.23
     range
    -0.23
    POSITIVE LOGITS
    çĻ¾å¹´
    0.28
     COPYING
    0.27
    uta
    0.27
    spr
    0.27
    åĢĴ
    0.26
    æĺł
    0.26
    Mapping
    0.26
    æĹł
    0.25
     mapper
    0.25
    enga
    0.25
    Activations Density 0.001%

    No Known Activations