© 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. 162104
    Prev
    Next
    INDEX
    Explanations

    will

    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
    åĩĢ
    -0.30
    å²Ĺ
    -0.26
    èĻŀ
    -0.26
    jos
    -0.25
    ç¨Ģ
    -0.25
    å¾Ħ
    -0.25
    ast
    -0.24
     compared
    -0.24
    olina
    -0.24
    yb
    -0.24
    POSITIVE LOGITS
    æ¸Ń
    0.28
     prób
    0.27
    å¾Ģäºĭ
    0.26
    ynamo
    0.26
    éĿŀ常好çļĦ
    0.25
     perhaps
    0.25
     Trad
    0.25
    é©¾æł¡
    0.24
     Moy
    0.24
     yaÄŁ
    0.24
    Activations Density 0.014%

    No Known Activations