© 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. 108342
    Prev
    Next
    INDEX
    Explanations

    Scientific names and etymologies

    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
    oti
    -0.35
    éĹ¹
    -0.26
    桯
    -0.25
    bout
    -0.24
    imen
    -0.24
    isse
    -0.24
    ihu
    -0.23
    åĬ¿
    -0.23
     leicht
    -0.23
    ipes
    -0.23
    POSITIVE LOGITS
    éĹª
    0.26
    ToFront
    0.25
    ximo
    0.25
     intended
    0.24
     ArgumentOutOfRangeException
    0.24
     analytical
    0.24
    èµıæŀIJ
    0.23
    æĦıæĢĿ
    0.23
    tw
    0.23
    ToLower
    0.23
    Activations Density 0.908%

    No Known Activations