© 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. 8800
    Prev
    Next
    INDEX
    Explanations

    ///

    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
     coal
    -0.27
    èĩŃ
    -0.26
    оп
    -0.26
    coal
    -0.26
     Sacr
    -0.25
    atori
    -0.25
     collapses
    -0.25
    æħ£
    -0.24
    æķij人
    -0.24
    BER
    -0.24
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.28
    iteDatabase
    0.27
    øy
    0.27
    ä¸Ģ群
    0.26
    ä¿ĿæĮģçĿĢ
    0.25
    让人们
    0.25
    emand
    0.25
    æİ¥åľ°æ°Ķ
    0.25
    ä¸Ģç»ı
    0.25
     ******************************************************************************↵
    0.25
    Activations Density 0.194%

    No Known Activations