© 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. 98475
    Prev
    Next
    INDEX
    Explanations

    2

    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
     And
    -0.19
    -O
    -0.19
    -K
    -0.17
    -M
    -0.17
    -D
    -0.17
    -H
    -0.17
    -h
    -0.17
    -ch
    -0.17
    -R
    -0.16
    -G
    -0.16
    POSITIVE LOGITS
     Prostit
    0.32
    å°±æĿ¥çľĭçľĭ
    0.28
     bureaucr
    0.26
     sodom
    0.26
     intox
    0.25
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.25
    毫æĹłçĸij
    0.25
    æĹłè®ºæĺ¯åħ¶
    0.24
    åĨįä¹Łä¸į
    0.24
    æį¢åı¥è¯Ŀ
    0.24
    Activations Density 0.010%

    No Known Activations