© 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. 23116
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ä¸Ģ段
    -0.27
    asp
    -0.25
    åIJ¸å¼ķ
    -0.25
    åIJ¸å¼ķäºĨ
    -0.24
    äºĨä¸Ģ个
    -0.24
    ä¸Ģ个å¤ļ
    -0.24
    egree
    -0.24
    racial
    -0.23
    incipal
    -0.23
     Vest
    -0.23
    POSITIVE LOGITS
    ä¹ĭ家
    0.32
    åĵĤ
    0.27
     verbosity
    0.27
    ainers
    0.26
    igne
    0.26
    ensburg
    0.25
    ighton
    0.25
    inel
    0.25
    æ³»
    0.25
    Ĥ¹
    0.24
    Activations Density 0.000%

    No Known Activations