© 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. 23-TRANSCODER-HP
    7. 24999
    Prev
    Next
    INDEX
    Explanations

    Language and questions

    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
    ç»Ŀ大å¤ļæķ°
    -0.27
    说æĺİ书
    -0.26
     Compare
    -0.26
    عÙĦا
    -0.26
    Compare
    -0.26
    æĺ¯æ¯Ķè¾ĥ
    -0.26
     cess
    -0.26
    çĶľ
    -0.25
    åĨ³å®ļ
    -0.25
    æ¯Ķè¾ĥ
    -0.24
    POSITIVE LOGITS
    ponsors
    0.28
    éĽī
    0.27
    iske
    0.26
    phans
    0.25
    çļĦçIJĨ念
    0.25
    asers
    0.25
    ccoli
    0.25
     upon
    0.24
    ingles
    0.24
    obia
    0.24
    Activations Density 0.003%

    No Known Activations