© 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. 57408
    Prev
    Next
    INDEX
    Explanations

    Code and legal jargon

    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
    ainless
    -0.32
    票
    -0.28
     polling
    -0.27
    eph
    -0.27
     tim
    -0.26
     nto
    -0.25
    ston
    -0.25
    ä¸įåħģ许
    -0.25
    éĻį
    -0.25
    (GLFW
    -0.25
    POSITIVE LOGITS
     Diss
    0.26
    é¾ĥ
    0.26
    ramework
    0.26
    ÐĵлавнаÑı
    0.26
    fault
    0.25
    endor
    0.25
    æ¶İ
    0.24
     Reached
    0.24
     favorable
    0.23
    oodoo
    0.23
    Activations Density 0.000%

    No Known Activations