© 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. 23806
    Prev
    Next
    INDEX
    Explanations

    statistics

    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
    éĿŀæ³ķ
    -0.29
     Enterprises
    -0.27
     tale
    -0.27
     Truyá»ģn
    -0.26
    vang
    -0.25
    èĥį
    -0.25
    éĢįéģ¥
    -0.24
    æĺ¯ä¸įåı¯èĥ½
    -0.24
     imb
    -0.24
    emb
    -0.23
    POSITIVE LOGITS
    asaki
    0.29
    åħ¨èµĦ
    0.28
     cork
    0.26
    åĩĨå¤ĩ
    0.26
    交ç»Ļ
    0.25
    roke
    0.25
    ä¾Ľå¤§å®¶
    0.25
     Tomb
    0.25
    æµħ
    0.25
    å½»åºķ
    0.24
    Activations Density 0.005%

    No Known Activations