© 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. 24650
    Prev
    Next
    INDEX
    Explanations

    sevent

    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
    soles
    -0.26
    нал
    -0.25
     Prefer
    -0.24
    çķª
    -0.24
    ↵            ↵
    -0.24
    kek
    -0.24
    æĽ´æĺ¯
    -0.24
     fir
    -0.23
    å°ijä¸įäºĨ
    -0.23
     Tar
    -0.23
    POSITIVE LOGITS
    oenix
    0.31
    è¿©
    0.30
    iez
    0.27
    atically
    0.27
    eled
    0.26
    eight
    0.26
    eme
    0.26
    ing
    0.26
    anst
    0.26
    enders
    0.25
    Activations Density 0.056%

    No Known Activations