© 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. 108994
    Prev
    Next
    INDEX
    Explanations

    Code/numerical context

    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
     seventh
    -0.38
     sixth
    -0.36
     six
    -0.36
     seven
    -0.35
    第ä¸ĥ
    -0.35
     eighth
    -0.34
     seventy
    -0.33
    åħŃ个æľĪ
    -0.33
     Seventh
    -0.33
     ninth
    -0.32
    POSITIVE LOGITS
    isecond
    0.30
    istribute
    0.28
    2
    0.28
    -boy
    0.27
    äºĮæĺ¯
    0.27
    lege
    0.26
    3
    0.26
    imary
    0.25
    ä¸ĢåŃ£åº¦
    0.23
     bend
    0.22
    Activations Density 0.942%

    No Known Activations