© 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. 162763
    Prev
    Next
    INDEX
    Explanations

    artistic works and music

    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
    åĵ¥ä»¬
    -0.26
    ä¸ī大éĺ¶æ®µ
    -0.25
    pill
    -0.24
    eway
    -0.24
    é¦ĸ次
    -0.23
     Ñĩел
    -0.23
     Rencontres
    -0.23
    è°ģçŁ¥éģĵ
    -0.23
     tang
    -0.23
     Resistance
    -0.23
    POSITIVE LOGITS
    rodu
    0.27
    çģ«çĥŃ
    0.26
    Serve
    0.25
    ä½ĵçİ°
    0.25
    ardu
    0.25
    æ²ī
    0.25
    icher
    0.25
    ares
    0.25
    èŀŁ
    0.24
    agedList
    0.24
    Activations Density 0.013%

    No Known Activations