© 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. 112004
    Prev
    Next
    INDEX
    Explanations

    Questions, conjunctions, punctuation

    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
    两èĢħ
    -0.94
    äºĮèĢħ
    -0.93
     both
    -0.89
    both
    -0.89
    Both
    -0.85
     Both
    -0.84
    è¿Ļ两个
    -0.83
    è¿Ļ两ç§į
    -0.78
    è¿Ļ两
    -0.78
    _both
    -0.74
    POSITIVE LOGITS
     all
    0.46
    æīĢæľī
    0.40
    æīĢæľīçļĦ
    0.40
    all
    0.40
    ãģ©ãĤĮ
    0.39
    åħ¨éĥ¨
    0.39
    —all
    0.38
    åħ¨ãģ¦
    0.37
    (all
    0.36
    	all
    0.36
    Activations Density 0.001%

    No Known Activations