© 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. 22-TRANSCODER-HP
    7. 98563
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    丧
    -0.29
    èµ¢
    -0.26
    orgia
    -0.26
    ä½ľæĪĺ
    -0.25
    Collision
    -0.25
    PROTO
    -0.25
    essor
    -0.25
    ö
    -0.24
     klar
    -0.24
    å«ģ
    -0.24
    POSITIVE LOGITS
     Lump
    0.29
    IBC
    0.27
    anus
    0.27
    unal
    0.27
     Pais
    0.26
    å¤ĩçĶ¨
    0.25
    æĸ¹æīį
    0.25
     Bookmark
    0.25
    åij½ä¸Ń
    0.24
    วà¸Ķ
    0.24
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.