© 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. 31-TRANSCODER-HP
    7. 18796
    Prev
    Next
    INDEX
    Explanations

    interest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isper
    -0.29
    (rp
    -0.27
     Convenience
    -0.26
    licing
    -0.26
    inning
    -0.26
    å¢Ļä¸Ĭ
    -0.25
    pray
    -0.25
     Alibaba
    -0.25
    ç²Ĵ
    -0.25
    Canon
    -0.25
    POSITIVE LOGITS
     interest
    0.41
     interests
    0.37
    çļĦåĪ©çĽĬ
    0.37
    åĪ©çĽĬ
    0.33
    -interest
    0.33
     Interest
    0.32
    æĦŁåħ´è¶£
    0.31
    interest
    0.29
    åħ´è¶£
    0.29
    Interest
    0.29
    Activations Density 0.083%

    No Known Activations