© 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. 41945
    Prev
    Next
    INDEX
    Explanations

    code

    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
     surfaces
    -0.28
    èĶ·
    -0.26
    wig
    -0.26
    æĺ¯ä¸Ģ件
    -0.25
    èĩªæ²»
    -0.25
    aired
    -0.25
    hyper
    -0.25
    pected
    -0.25
    ä¸Ģ头
    -0.24
     genie
    -0.24
    POSITIVE LOGITS
    ese
    0.29
    äººåľ¨
    0.29
    渲æŁĵ
    0.27
    纪å¾ĭ
    0.26
     ChÆ°Æ¡ng
    0.25
    éľĢæ±Ĥ
    0.24
    æ¤Ĵ
    0.24
     ho
    0.24
    æīĺ
    0.24
     Order
    0.24
    Activations Density 0.002%

    No Known Activations