© 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. 87622
    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
    è¿ĺæľª
    -0.27
    brief
    -0.27
    è®©ä½ł
    -0.27
    gü
    -0.26
    Prompt
    -0.26
    æ¹Ľ
    -0.25
    á»įng
    -0.25
    è´Łè´£
    -0.24
    ÙĤب
    -0.24
    KN
    -0.24
    POSITIVE LOGITS
    IGIN
    0.26
    onic
    0.25
     _:
    0.24
    çĪ±åĽ½ä¸»ä¹ī
    0.24
    èµ³
    0.24
    å·¨åŀĭ
    0.23
     Buff
    0.23
    ))?
    0.23
    è´ŁéĿ¢
    0.23
    {@
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.