© 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. 43288
    Prev
    Next
    INDEX
    Explanations

    large, big

    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
     small
    -0.46
    small
    -0.42
     Small
    -0.42
    Small
    -0.41
    å°ı
    -0.37
     large
    -0.35
     significant
    -0.34
    mall
    -0.34
    large
    -0.34
    å¾Ī大
    -0.32
    POSITIVE LOGITS
    æºIJ头
    0.31
    -picture
    0.26
    xing
    0.26
     strm
    0.25
     efficiency
    0.24
    imity
    0.24
    çĻ¾å®¶
    0.24
    æĭ¿æĿ¥
    0.24
    áln
    0.24
    ÑİÑīиÑħ
    0.23
    Activations Density 0.005%

    No Known Activations