© 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. 12-TRANSCODER-HP
    7. 23325
    Prev
    Next
    INDEX
    Explanations

    Snippets of various texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ãłn
    -0.30
    ä¸Ģ大æī¹
    -0.28
    æīĢæľī人
    -0.26
    åIJ¬å®Į
    -0.25
    èĶ
    -0.24
     uncon
    -0.24
    RIC
    -0.24
    ãģ¨æĢĿãģĨ
    -0.24
     conferences
    -0.24
    ç¶ĵ
    -0.24
    POSITIVE LOGITS
    æľºæ¢°åĮĸ
    0.27
     {"
    0.26
     Mess
    0.26
    -ish
    0.26
    ToJson
    0.25
    kb
    0.25
    -utils
    0.24
    FormatException
    0.24
    æĪĺæĸĹåĬĽ
    0.24
    INAL
    0.24
    Activations Density 0.000%

    No Known Activations