© 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. 57829
    Prev
    Next
    INDEX
    Explanations

    rows

    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
    TU
    -0.30
    裾
    -0.29
     twist
    -0.28
    âİ¥
    -0.28
     Jah
    -0.26
    享
    -0.26
    èĥ½æºIJ
    -0.25
    igung
    -0.25
    çļĦçĶ»éĿ¢
    -0.25
     exh
    -0.24
    POSITIVE LOGITS
    estroy
    0.29
    ective
    0.28
    cki
    0.28
    ault
    0.27
    åĢĴå¡Į
    0.26
     Sonata
    0.25
    allax
    0.25
    ally
    0.25
    olid
    0.25
    æľŁåĨħ
    0.25
    Activations Density 0.049%

    No Known Activations