© 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. 32-TRANSCODER-HP
    7. 43242
    Prev
    Next
    INDEX
    Explanations

    "Old"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽ½å®¶
    -0.78
    åľĭ家
    -0.63
     êµŃê°Ģ
    -0.44
    åĽ½åº¦
    -0.38
     national
    -0.33
    national
    -0.31
    åĽ½å®¶çº§
    -0.30
     nation
    -0.30
     country
    -0.30
    ä¸ªåĽ½å®¶
    -0.29
    POSITIVE LOGITS
     Old
    0.59
    Old
    0.50
     Middle
    0.47
    Middle
    0.41
     OLD
    0.37
    _old
    0.35
     old
    0.32
    OLD
    0.31
    -old
    0.30
     Proto
    0.30
    Activations Density 0.001%

    No Known Activations