© 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. 29468
    Prev
    Next
    INDEX
    Explanations

    has

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įèĤ¯
    -0.26
    /embed
    -0.26
    accessible
    -0.25
    饺
    -0.24
    é¡¹çĽ®çļĦ
    -0.24
    shall
    -0.23
    cts
    -0.23
    libft
    -0.23
    å·¢
    -0.23
    æįįåį«
    -0.23
    POSITIVE LOGITS
    ÐŀÐł
    0.28
     thrott
    0.26
    æĦı
    0.26
    DROP
    0.26
    mpz
    0.25
    ç§Ĵ
    0.25
     disag
    0.25
    esty
    0.24
    ears
    0.24
     differ
    0.24
    Activations Density 1.981%

    No Known Activations