© 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. 27-TRANSCODER-HP
    7. 9512
    Prev
    Next
    INDEX
    Explanations

    Erroneous strings and phone numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¤IJ
    -0.27
     Synopsis
    -0.27
    æ¼ı
    -0.27
    SEA
    -0.26
    __.__
    -0.26
    åĬŁåĬĽ
    -0.26
    //=
    -0.25
    imson
    -0.25
     >>=
    -0.24
    xed
    -0.24
    POSITIVE LOGITS
    éĿ¢è¯ķ
    0.27
    åİĺ
    0.26
    åĴļ
    0.25
     conver
    0.25
    itch
    0.24
     merc
    0.24
    ä¸Ģå¼ł
    0.24
    (div
    0.23
     stitch
    0.23
    ãĤ³ãĥŁãĥ¥ãĥĭãĤ±ãĥ¼ãĤ·ãĥ§ãĥ³
    0.23
    Activations Density 0.001%

    No Known Activations