© 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. 27-TRANSCODER-HP
    7. 8023
    Prev
    Next
    INDEX
    Explanations

    code reuse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    管çIJĨ模å¼ı
    -0.29
    å½±åĥı
    -0.27
    éħįåģ¶
    -0.26
    @param
    -0.26
    模å¼ı
    -0.25
    rites
    -0.24
    ĵį
    -0.24
     Ops
    -0.23
     Pair
    -0.23
     ops
    -0.23
    POSITIVE LOGITS
    ifax
    0.28
    -widget
    0.27
    uters
    0.25
    å¤į
    0.25
    ivate
    0.25
    æ¼ĵ
    0.25
    æī¼
    0.24
    upert
    0.24
     widget
    0.24
     frequently
    0.24
    Activations Density 0.012%

    No Known Activations