© 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. 108033
    Prev
    Next
    INDEX
    Explanations

    code/copyright snippets

    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
    åĩĮ
    -0.35
     vein
    -0.27
    çķĮ第ä¸Ģ
    -0.26
    emm
    -0.25
    æĭ¢
    -0.25
    ìŀł
    -0.24
    两级
    -0.24
     Overrides
    -0.24
    oses
    -0.24
    imir
    -0.24
    POSITIVE LOGITS
    Driver
    0.28
     cour
    0.27
    çĸı
    0.27
     Anc
    0.25
    表æĥħ
    0.24
    å±Ģéĥ¨
    0.24
    iaux
    0.24
     bystand
    0.24
    æĹģ
    0.24
    é«ĵ
    0.23
    Activations Density 0.985%

    No Known Activations