© 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. 107642
    Prev
    Next
    INDEX
    Explanations

    Text excerpts from diverse sources

    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
    ogens
    -0.26
    æ´Ĺå¹²åĩĢ
    -0.26
     пÑĢеж
    -0.25
     Oasis
    -0.25
    æĥ§
    -0.25
    ogenic
    -0.24
    asil
    -0.24
    Editable
    -0.24
    raith
    -0.24
    ogonal
    -0.24
    POSITIVE LOGITS
    å¾®å¦Ļ
    0.30
     Stam
    0.29
    æĺİæĹ¥
    0.27
    èĻ¬
    0.26
    æ¯ĶèµĽä¸Ń
    0.25
    éĺĸ
    0.25
    åIJ¬çĿĢ
    0.25
    kel
    0.25
    æ·¡æ·¡çļĦ
    0.25
    opot
    0.24
    Activations Density 0.288%

    No Known Activations