© 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. 107868
    Prev
    Next
    INDEX
    Explanations

    technical or foreign content

    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
    çĶļä¹Ī
    -0.40
    ä¸įåħĭä¸įåıĬ
    -0.39
    é»ī
    -0.34
    æĽ©
    -0.32
    çĿģå¼Ģ
    -0.32
    ãeste
    -0.30
     comprehend
    -0.30
    Ú
    -0.29
    éĢĿä¸ĸ
    -0.29
     dependable
    -0.28
    POSITIVE LOGITS
     ↵
    0.29
    éĥħ
    0.27
    éĶĻ
    0.26
    illé
    0.26
    arently
    0.26
    fav
    0.26
    -↵
    0.25
    illon
    0.25
    ·
    0.25
    Ä±ÅŁÄ±
    0.24
    Activations Density 1.940%

    No Known Activations