© 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. 22-TRANSCODER-HP
    7. 98864
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Braz
    -0.30
     bite
    -0.29
    ä¸įå½±åĵį
    -0.27
    Become
    -0.26
    讲究
    -0.26
    ategory
    -0.25
     matter
    -0.25
    dev
    -0.25
     burn
    -0.24
    çĨ¨
    -0.24
    POSITIVE LOGITS
    å°¼äºļ
    0.27
    زاد
    0.27
    æ¯ıä¸Ģ
    0.26
    lian
    0.26
    åıijçĶŁäºĨ
    0.25
    é²Ĭ
    0.25
    åĪĿ次
    0.25
    壮大
    0.25
    udeau
    0.24
    课
    0.24
    Activations Density 0.002%

    No Known Activations