© 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. 87318
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    @endsection
    -0.26
    åĩłä¹İ没æľī
    -0.25
    ä¸įåħ·å¤ĩ
    -0.25
    ãģ§ãģ¯ãģªãģı
    -0.24
     oss
    -0.24
    æĹłéľĢ
    -0.24
     teardown
    -0.24
    ä¸įåIJ«
    -0.23
     instead
    -0.23
     slice
    -0.23
    POSITIVE LOGITS
    以ä¸Ĭ
    0.29
    ç³»
    0.28
    ioned
    0.27
    åģļ
    0.27
    以ä¸ĬçļĦ
    0.26
    æĺıè¿·
    0.26
    å·¥ä½ľ
    0.26
    aku
    0.26
    æ»´
    0.26
    above
    0.26
    Activations Density 0.018%

    No Known Activations