© 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. 43257
    Prev
    Next
    INDEX
    Explanations

    ri

    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
    ijľ
    -0.29
     har
    -0.28
    har
    -0.25
     forks
    -0.25
    ousse
    -0.24
    .decode
    -0.24
    ham
    -0.24
    åľ¨è¿Ļ个
    -0.24
    æĻķ
    -0.23
    degrees
    -0.23
    POSITIVE LOGITS
     van
    0.36
     even
    0.30
    chap
    0.29
    çĶļèĩ³
    0.29
    even
    0.29
    olland
    0.28
     ter
    0.27
     Even
    0.26
    Van
    0.26
     Van
    0.26
    Activations Density 0.009%

    No Known Activations