© 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. 95946
    Prev
    Next
    INDEX
    Explanations

    biological molecules

    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
    èĤĮ
    -0.28
    åĢĻéĢī
    -0.28
    .gstatic
    -0.28
    ĽĦ
    -0.28
    agram
    -0.26
    ellar
    -0.26
    ENU
    -0.25
    ville
    -0.25
     Pols
    -0.25
    ç®Ķ
    -0.25
    POSITIVE LOGITS
     emitter
    0.28
    fall
    0.25
    cies
    0.24
    è¶ħé«ĺ
    0.24
    ehler
    0.24
     multis
    0.23
    -unstyled
    0.23
     multicultural
    0.23
    Jam
    0.23
    nahme
    0.23
    Activations Density 0.939%

    No Known Activations