© 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. 107444
    Prev
    Next
    INDEX
    Explanations

    nor

    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
    gers
    -0.28
    Ñħодим
    -0.28
    æĮİ
    -0.25
    èħĶ
    -0.24
    ÃŃo
    -0.24
    çĪ±ä½ł
    -0.23
     (...
    -0.23
     tall
    -0.23
     Append
    -0.23
    æİ°
    -0.22
    POSITIVE LOGITS
    æ¸IJ
    0.31
    elight
    0.30
    thern
    0.30
    atitude
    0.27
    èĤ¡
    0.25
    ptoms
    0.24
    outine
    0.24
    æ¯Ĵ
    0.24
    osphere
    0.24
    otoxic
    0.23
    Activations Density 0.284%

    No Known Activations