© 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. 108021
    Prev
    Next
    INDEX
    Explanations

    code and copyright notices

    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
     Shuttle
    -0.26
    liner
    -0.26
     test
    -0.26
    ten
    -0.25
     YE
    -0.25
    tos
    -0.25
    å¿ħå¤ĩ
    -0.24
    [âĢ¦
    -0.24
    æ¦Ĥ
    -0.24
    Outlet
    -0.24
    POSITIVE LOGITS
    burgh
    0.36
    åŁºæķ°
    0.28
    æĪĺ绩
    0.28
    logan
    0.26
    æĪIJéķ¿ä¸º
    0.26
    ence
    0.26
    eka
    0.25
    ohana
    0.25
    忤
    0.25
     nowrap
    0.25
    Activations Density 0.035%

    No Known Activations