© 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. 40568
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    åĿĹ
    -0.28
     persisted
    -0.26
    为ä¼ģä¸ļ
    -0.26
    åĤ¨å¤ĩ
    -0.25
    adf
    -0.25
     Bars
    -0.25
    é»ijå¤ľ
    -0.25
    ucking
    -0.25
    ç§ī
    -0.25
    ELS
    -0.24
    POSITIVE LOGITS
    Łèĥ½
    0.28
    haus
    0.28
    vo
    0.28
    cycl
    0.26
    andal
    0.26
     Kap
    0.25
    å¥Ķ
    0.24
    ige
    0.24
    het
    0.24
    (eval
    0.24
    Activations Density 1.818%

    No Known Activations