© 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. 18973
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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
     Rap
    -0.27
     needs
    -0.26
     Needs
    -0.26
    åĩĨå¤ĩ
    -0.25
    more
    -0.25
    .hasMore
    -0.25
    More
    -0.25
     More
    -0.25
    OS
    -0.25
    æĽ´å¤ļä¿¡æģ¯
    -0.25
    POSITIVE LOGITS
     anywhere
    0.44
     left
    0.41
    ä»»ä½ķ人
    0.39
     anytime
    0.36
     Anything
    0.36
    ä»»ä½ķ
    0.35
     accepted
    0.35
     anything
    0.34
     rejected
    0.33
    accepted
    0.33
    Activations Density 0.010%

    No Known Activations