© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161748
    Prev
    Next
    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.35
    currently
    -0.33
    缮åīį
    -0.30
     presently
    -0.29
    cribe
    -0.29
    å½ĵåīį
    -0.28
     Currently
    -0.26
    姱
    -0.26
    gan
    -0.25
    aket
    -0.25
    POSITIVE LOGITS
    æķħ
    0.42
    æīĢä»¥åľ¨
    0.32
     hence
    0.31
    å¸ĮæľĽ
    0.31
    éģ¿åħį
    0.29
    为äºĨéģ¿åħį
    0.29
    éĺ²æŃ¢
    0.29
    ç¡®ä¿Ŀ
    0.27
     Hence
    0.26
    åĽłæѤ
    0.26
    Activations Density 0.006%

    No Known Activations