© 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. 97876
    Prev
    Next
    INDEX
    Explanations

    obligation

    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
     consequence
    -0.33
    è¾ľè´Ł
    -0.30
    ä¸įåħį
    -0.30
    åıĹåĪ°å½±åĵį
    -0.29
    çīºçī²
    -0.29
    ãģ«ãģªãģ£ãģ¦ãģĹãģ¾ãģĨ
    -0.28
    ailing
    -0.27
     inevitably
    -0.26
     encounters
    -0.26
    éĥ½éľĢè¦ģ
    -0.26
    POSITIVE LOGITS
    confirm
    0.27
    åı¯èĥ½æĢ§
    0.27
     convinc
    0.27
    arton
    0.27
     confirm
    0.27
    portun
    0.26
    æĸ¹åIJij
    0.26
     Confirm
    0.26
    berman
    0.25
    -License
    0.25
    Activations Density 0.009%

    No Known Activations