© 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. 24-TRANSCODER-HP
    7. 150758
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utta
    -0.29
    åıªä¸įè¿ĩ
    -0.28
    lov
    -0.26
    ë£Į
    -0.26
     sea
    -0.26
    æĿĢäºĨ
    -0.26
     Satan
    -0.25
    åıªä¸įè¿ĩæĺ¯
    -0.25
    æľīçļĦ人
    -0.25
     merely
    -0.25
    POSITIVE LOGITS
    便äºİ
    0.29
    VL
    0.29
     flotation
    0.28
    owie
    0.26
    osten
    0.25
    hä
    0.25
    ELY
    0.25
     audition
    0.24
    approved
    0.24
    ologically
    0.24
    Activations Density 0.142%

    No Known Activations