© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 140877
    Prev
    Next
    INDEX
    Explanations

    -year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à²ļ
    -0.29
    åħ·ä½ĵçļĦ
    -0.27
    è·³
    -0.27
    éĽĨæĪIJ
    -0.26
    è¶Ĭ
    -0.26
    è·ĥ
    -0.26
    dera
    -0.26
    满
    -0.25
    åħ·ä½ĵ
    -0.25
    ä¿¡
    -0.24
    POSITIVE LOGITS
     mont
    0.27
    对çħ§æ£ĢæŁ¥
    0.27
    fault
    0.27
     fault
    0.26
    縱
    0.25
     faults
    0.25
    urses
    0.25
    ´t
    0.25
    mont
    0.25
    ç½ij讯
    0.25
    Activations Density 1.840%

    No Known Activations