© 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. 14-TRANSCODER-HP
    7. 39953
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anken
    -0.30
    _ASCII
    -0.28
    åįģéĩĮ
    -0.28
     Appet
    -0.26
    {}'.
    -0.26
    èĩªè¡Į
    -0.25
     pian
    -0.25
    å®ĺæĸ¹å¾®ä¿¡
    -0.24
    $product
    -0.24
    estic
    -0.24
    POSITIVE LOGITS
    è¯Ŀ说
    0.28
     Cecil
    0.27
    brate
    0.26
    Or
    0.26
    大èĥĨ
    0.25
    focus
    0.25
    osaurs
    0.25
    èĻ«
    0.25
    讲
    0.24
    boarding
    0.24
    Activations Density 2.988%

    No Known Activations