© 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. 111474
    Prev
    Next
    INDEX
    Explanations

    internet snippets

    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
    chip
    -0.29
    strt
    -0.24
    /gtest
    -0.24
    Chip
    -0.24
    åĩºäºĨ
    -0.23
    arger
    -0.23
    äs
    -0.23
    身ä¸Ĭ
    -0.23
    бил
    -0.23
    bill
    -0.23
    POSITIVE LOGITS
    åĴ¨è¯¢æľįåĬ¡
    0.27
    ymes
    0.25
    å½ĵæĪij
    0.25
    Als
    0.25
    .every
    0.24
    çĴ§
    0.24
    æīĺ
    0.23
    quette
    0.23
    Writable
    0.23
    falls
    0.23
    Activations Density 0.004%

    No Known Activations