© 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. 96176
    Prev
    Next
    INDEX
    Explanations

    time

    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
    浸
    -0.29
     Skywalker
    -0.28
    ष
    -0.28
    æłijæŀĹ
    -0.26
    丼æŀĹ
    -0.26
    =yes
    -0.25
     waterfall
    -0.24
    ilinear
    -0.23
    ardy
    -0.23
    湿
    -0.23
    POSITIVE LOGITS
     Translate
    0.27
    ç´¢
    0.27
    atter
    0.27
    解å¼Ģ
    0.26
    åĪĨåŃIJ
    0.26
    nicos
    0.25
     Canary
    0.24
    mime
    0.24
     Decom
    0.24
    dependence
    0.24
    Activations Density 0.888%

    No Known Activations