© 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. 97735
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    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
    _ctxt
    -0.25
    нии
    -0.25
    âĶĢâĶĢ
    -0.25
     sát
    -0.24
    that
    -0.24
    raits
    -0.23
     convey
    -0.23
     Amen
    -0.23
    OUNDS
    -0.23
     Discuss
    -0.23
    POSITIVE LOGITS
    åı¦æľī
    0.31
    åľ¨å¤ĸ
    0.30
    åı¦
    0.29
    åı¦è¡Į
    0.29
     secs
    0.27
    hoe
    0.26
    _secs
    0.26
    åľ¨å¤ĸéĿ¢
    0.26
    ä¸įèµ·
    0.25
     removeAll
    0.24
    Activations Density 0.013%

    No Known Activations