© 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. 108028
    Prev
    Next
    INDEX
    Explanations

    location or origin

    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
    ãģĹãģŁãĤĤãģ®
    -0.29
    äºİæѤ
    -0.27
    éĥ½ä¼ļæľī
    -0.27
    æĢ»éĺŁ
    -0.26
    adesh
    -0.26
    unos
    -0.26
    æīĢæıIJä¾ĽçļĦ
    -0.25
     choice
    -0.25
    esion
    -0.24
    åı¯ä»¥éĢīæĭ©
    -0.24
    POSITIVE LOGITS
     located
    0.40
    ä½įäºİ
    0.30
     comes
    0.30
     derived
    0.30
     li
    0.29
     come
    0.29
     situated
    0.29
    æºIJèĩª
    0.28
     lies
    0.28
     resides
    0.27
    Activations Density 1.223%

    No Known Activations