© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109392
    Prev
    Next
    INDEX
    Explanations

    electric

    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
    Negative Logits
    heits
    -0.27
    опÑĢеделен
    -0.26
     Nights
    -0.26
    ãĤĤãģ®ãģ§ãģĻ
    -0.25
    aoke
    -0.25
    cased
    -0.24
     someday
    -0.24
    cross
    -0.24
     Cros
    -0.24
    æĭ¿åĩº
    -0.24
    POSITIVE LOGITS
    Īĺ
    0.33
     priced
    0.28
    æĸ¯å¡Ķ
    0.26
    och
    0.25
    æĪĺ
    0.25
     cheered
    0.25
    icients
    0.25
    èĦĤ
    0.25
    ACHE
    0.24
    aty
    0.24
    Activations Density 0.965%

    No Known Activations