© 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. 27-TRANSCODER-HP
    7. 57768
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imal
    -0.30
    æĽ´å¥½çļĦ
    -0.27
     dynamics
    -0.27
    osaur
    -0.26
    åŁ
    -0.26
    ech
    -0.25
    åĪĿæľŁ
    -0.25
     Tomb
    -0.24
     mơ
    -0.24
    è£Ĥ
    -0.24
    POSITIVE LOGITS
    说æĺİ书
    0.29
    IVATE
    0.27
    elsen
    0.26
    opup
    0.25
    KÄ°
    0.25
     Infinity
    0.24
     engineered
    0.24
    ä¸ŃåĽ½åĪ¶éĢł
    0.24
     patented
    0.24
     territorial
    0.24
    Activations Density 0.002%

    No Known Activations