© 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. 40510
    Prev
    Next
    INDEX
    Explanations

    depending

    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
    次
    -0.26
    åķĨåĵģæĪ¿
    -0.26
    gi
    -0.26
    bio
    -0.24
    gin
    -0.24
    หมà¸Ķ
    -0.24
    æ¦Ľ
    -0.24
    ç¨İåĬ¡æĢ»å±Ģ
    -0.23
    åįķä½į
    -0.23
    Amazon
    -0.23
    POSITIVE LOGITS
    çĥŁçģ«
    0.28
    assembly
    0.27
    å¤ļåIJĥ
    0.25
     nonetheless
    0.25
     Clem
    0.24
    ourney
    0.24
    åĪ©çī©
    0.24
     popping
    0.24
    å·©
    0.24
    ascript
    0.24
    Activations Density 2.430%

    No Known Activations