© 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. 20-TRANSCODER-HP
    7. 141580
    Prev
    Next
    INDEX
    Explanations

    Disjointed snippets of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èī°éļ¾
    -0.45
    éļ¾
    -0.41
     difficult
    -0.37
    èī°è¾Ľ
    -0.37
    èī°èĭ¦
    -0.35
     challenging
    -0.35
    æľĢéļ¾
    -0.35
     tricky
    -0.34
    éļ¾åº¦
    -0.34
    éĽ£
    -0.33
    POSITIVE LOGITS
     conveniently
    0.32
    arella
    0.29
    æĹ¢åı¯ä»¥
    0.28
    amage
    0.28
    å®ĮåĸĦçļĦ
    0.27
    lus
    0.26
    onomous
    0.26
     Grü
    0.25
    colon
    0.25
     anchored
    0.24
    Activations Density 57.593%

    No Known Activations