© 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. 108210
    Prev
    Next
    INDEX
    Explanations

    communic

    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
    .Pixel
    -0.26
    ÑĢо
    -0.26
    åĮ¿åIJį
    -0.26
    è¿ľ
    -0.25
    /umd
    -0.25
    /licenses
    -0.24
     far
    -0.24
    æ·ĺæ±°
    -0.24
    antar
    -0.24
    丼æŀĹ
    -0.23
    POSITIVE LOGITS
    éĴµ
    0.28
    æĿĸ
    0.28
     taps
    0.28
     pharmacies
    0.26
     tapping
    0.26
     tap
    0.26
    eload
    0.25
     Trials
    0.25
    tone
    0.25
     tones
    0.25
    Activations Density 0.890%

    No Known Activations