© 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. 108315
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
    uing
    -0.28
     curs
    -0.26
     advantage
    -0.25
    å´Ľèµ·
    -0.24
    æľ¬æľŁ
    -0.24
    éĢŁåº¦å¿«
    -0.24
    å¿«
    -0.24
    entes
    -0.24
    elves
    -0.24
    çļĦæĪ¿åŃIJ
    -0.23
    POSITIVE LOGITS
     Che
    0.28
    ACKET
    0.27
    acket
    0.26
    icers
    0.25
     anz
    0.24
     chaired
    0.24
     mortal
    0.24
     kid
    0.24
     Че
    0.23
    OLA
    0.23
    Activations Density 0.952%

    No Known Activations