© 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. 24094
    Prev
    Next
    INDEX
    Explanations

    interview 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
     اÙĦÙħØŃ
    -0.28
     furn
    -0.25
    iver
    -0.24
    indre
    -0.24
    çĻ¾å®¶
    -0.24
    arry
    -0.24
    ients
    -0.24
    ith
    -0.23
    aux
    -0.23
    sters
    -0.23
    POSITIVE LOGITS
     advice
    0.38
     Advice
    0.35
     memorable
    0.35
    éļ¾å¿ĺ
    0.34
    æľĢéļ¾
    0.33
     memories
    0.32
    æľĢåĸľæ¬¢
    0.32
     toughest
    0.32
    æľĢåĸľæ¬¢çļĦ
    0.32
     Memories
    0.31
    Activations Density 0.016%

    No Known Activations