© 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. 30-TRANSCODER-HP
    7. 95468
    Prev
    Next
    INDEX
    Explanations

    nice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onte
    -0.31
    纱
    -0.27
    imson
    -0.27
    ım
    -0.26
    iron
    -0.25
     irreversible
    -0.25
    èªĵè¨Ģ
    -0.25
    èĬ¨
    -0.25
     pragma
    -0.25
     reflecting
    -0.24
    POSITIVE LOGITS
     nice
    1.05
    nice
    1.00
    Nice
    0.87
     Nice
    0.85
     nic
    0.79
     nicely
    0.78
     nicer
    0.74
    nic
    0.73
     Nic
    0.65
    Nic
    0.60
    Activations Density 0.975%

    No Known Activations