© 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. 108757
    Prev
    Next
    INDEX
    Explanations

    code and dates

    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
    etus
    -0.27
    说å¾Ĺ
    -0.26
     boon
    -0.26
    phasis
    -0.25
    åģļçļĦ
    -0.25
    åģļå¾Ĺ
    -0.24
    è§ĤæľĽ
    -0.24
    ObjectContext
    -0.24
    apur
    -0.24
    spoken
    -0.24
    POSITIVE LOGITS
    ifies
    0.44
    å®ļäºĨ
    0.39
    ify
    0.35
    ä½ıäºĨ
    0.34
    izes
    0.33
     quantify
    0.31
    italize
    0.31
    elize
    0.30
     threw
    0.30
    å¼ĢäºĨ
    0.30
    Activations Density 1.895%

    No Known Activations