© 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. 41936
    Prev
    Next
    INDEX
    Explanations

    software licenses

    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
    GM
    -0.79
    (gs
    -0.75
    GR
    -0.75
    GS
    -0.74
    GC
    -0.71
     GM
    -0.71
    GP
    -0.71
    GPC
    -0.71
     GF
    -0.71
    GF
    -0.71
    POSITIVE LOGITS
    }\.[
    0.26
    æĬ¥ä¸ļ
    0.25
    åij¨è½¬
    0.24
    èĪ·
    0.23
    æ¾¥
    0.22
    çķ¤
    0.22
    .dataTables
    0.22
    eries
    0.21
    ç´Ĭä¹±
    0.21
    chester
    0.21
    Activations Density 0.013%

    No Known Activations