© 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. 88470
    Prev
    Next
    INDEX
    Explanations

    increasing

    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
    .TabIndex
    -0.31
    失åİ»
    -0.29
    ä¾Ŀ
    -0.28
    失åİ»äºĨ
    -0.28
     became
    -0.27
     drift
    -0.27
    æĪIJäºĨ
    -0.26
    abb
    -0.25
    è¡£
    -0.25
    VERS
    -0.25
    POSITIVE LOGITS
    æŃ£åľ¨
    0.27
    æ´Ĺæīĭ
    0.27
     than
    0.26
     gì
    0.25
    /issues
    0.25
    è¿ĻæĦıåij³çĿĢ
    0.25
     rooting
    0.25
    _than
    0.24
    ç¬ijçĿĢ
    0.24
    -than
    0.24
    Activations Density 0.032%

    No Known Activations