© 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. 97722
    Prev
    Next
    INDEX
    Explanations

    the

    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
     restriction
    -0.27
    åĴĮ
    -0.26
    otted
    -0.25
    ål
    -0.25
    @",
    -0.24
    被åĪĹåħ¥
    -0.24
    enberg
    -0.24
    ä¸ĭ
    -0.24
     exerc
    -0.24
    [array
    -0.23
    POSITIVE LOGITS
    æĹ¢æľī
    0.41
     BOTH
    0.37
     both
    0.37
    both
    0.36
    æĹ¢æĺ¯
    0.35
    ä¼ģä¸ļåĴĮ
    0.35
    æĹ¢
    0.34
    è´¨éĩıåĴĮ
    0.33
    Both
    0.33
    æĹ¢åı¯ä»¥
    0.33
    Activations Density 0.002%

    No Known Activations