© 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. 109112
    Prev
    Next
    INDEX
    Explanations

    of

    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
    rand
    -0.28
    åĨħçļĦ
    -0.27
    uur
    -0.27
    产ä¸ļéĽĨ群
    -0.26
    amat
    -0.26
    马ä¸Ĭ
    -0.26
    太大
    -0.25
    RAND
    -0.25
    éĺ¶
    -0.24
    jan
    -0.24
    POSITIVE LOGITS
    =device
    0.27
    轩
    0.26
     optics
    0.26
    误åĮº
    0.24
    家éĥ½çŁ¥éģĵ
    0.23
    _el
    0.23
    (device
    0.23
     device
    0.23
    LOCKS
    0.23
    device
    0.23
    Activations Density 0.113%

    No Known Activations