© 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. 32-TRANSCODER-HP
    7. 42807
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -0.43
    with
    -0.40
    With
    -0.40
    _with
    -0.38
     With
    -0.37
    WithData
    -0.36
     withString
    -0.33
    -with
    -0.33
    _WITH
    -0.32
    WITH
    -0.32
    POSITIVE LOGITS
     sweat
    0.31
    balls
    0.28
     joy
    0.28
     held
    0.28
     holy
    0.27
     infinite
    0.26
    æĸ°çĶŁ
    0.26
    主æĿĥ
    0.26
     infinity
    0.26
    ãĤ¢ãĤ¦ãĥĪ
    0.26
    Activations Density 0.003%

    No Known Activations