© 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. 8537
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ãĤĦãģ¯ãĤĬ
    -0.28
     Residence
    -0.24
    iddle
    -0.24
    è°ħ
    -0.24
    ç»Ĵ
    -0.24
    ᾶ
    -0.24
    دÙĨÙĬ
    -0.24
    ises
    -0.24
    udge
    -0.24
    Storm
    -0.23
    POSITIVE LOGITS
     applied
    0.29
     traditionally
    0.29
     пÑĢинÑı
    0.28
     implemented
    0.28
    ynes
    0.27
     worn
    0.26
    æıIJåĩºçļĦ
    0.26
     attempted
    0.26
    getDb
    0.25
    ainter
    0.25
    Activations Density 0.007%

    No Known Activations