© 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. 9-TRANSCODER-HP
    7. 29235
    Prev
    Next
    INDEX
    Explanations

    enforcement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¯ĦåĪĨ
    -0.30
    è¾¾
    -0.30
     dut
    -0.30
     Cot
    -0.27
    éģĶ
    -0.26
    èĭĩ
    -0.26
    -rating
    -0.26
    è·ŁçĿĢ
    -0.26
    /dd
    -0.26
    æ±Ĥ
    -0.26
    POSITIVE LOGITS
    éħ¿éħĴ
    0.29
    è¾Ľè¾£
    0.28
    书æ³ķ家
    0.28
    è¯ģåĪ¸äº¤æĺĵ
    0.28
     Affero
    0.28
    åĬłæ²¹ç«Ļ
    0.27
    éĤ¸
    0.25
    ivec
    0.25
    esModule
    0.25
    á»ĭa
    0.25
    Activations Density 1.048%

    No Known Activations