© 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. 96247
    Prev
    Next
    INDEX
    Explanations

    free programming

    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
    è§Ĥä¼Ĺ
    -0.29
     audiences
    -0.28
     units
    -0.28
    游客
    -0.27
    Observers
    -0.27
    èĬľ
    -0.27
     Units
    -0.27
     viewers
    -0.26
     richer
    -0.26
    acent
    -0.26
    POSITIVE LOGITS
     free
    0.33
    programming
    0.29
    free
    0.27
    ä¾ĽåºĶ
    0.27
    ä¸ī级
    0.27
    uib
    0.26
     Mixing
    0.26
     oral
    0.26
    .ping
    0.26
    ibal
    0.25
    Activations Density 0.891%

    No Known Activations