© 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. 25-TRANSCODER-HP
    7. 108510
    Prev
    Next
    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acia
    -0.28
    -*
    -0.26
    turn
    -0.26
     '..
    -0.25
    ÃŃcul
    -0.25
    (diff
    -0.25
    isible
    -0.24
     Ledger
    -0.24
     '!
    -0.24
     nun
    -0.24
    POSITIVE LOGITS
    ä¿Ŀ
    0.31
    æĶ¾æīĭ
    0.28
    elfth
    0.27
    förder
    0.26
    ustr
    0.25
    راÙĨ
    0.24
    uchen
    0.24
    ellant
    0.24
    ä¸Ĭæ±½
    0.24
    çĺ¾
    0.24
    Activations Density 0.893%

    No Known Activations