© 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. 24-TRANSCODER-HP
    7. 150589
    Prev
    Next
    INDEX
    Explanations

    being around something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Time
    -0.27
     cep
    -0.27
    win
    -0.26
    -time
    -0.25
    unders
    -0.25
     just
    -0.25
     Stra
    -0.24
    جÙĬب
    -0.24
    è¿ĺ以为
    -0.24
    OCI
    -0.24
    POSITIVE LOGITS
    çݯç»ķ
    0.36
    çݯå¢ĥ
    0.33
    ä¸ĢåľĪ
    0.31
     environ
    0.31
    çݯå¢ĥä¿ĿæĬ¤
    0.29
    åĽ´ç»ķ
    0.28
    çĴ°å¢ĥ
    0.28
     environment
    0.28
    çĴ°
    0.27
    ç¹ŀ
    0.27
    Activations Density 1.433%

    No Known Activations