© 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. 32-TRANSCODER-HP
    7. 43725
    Prev
    Next
    INDEX
    Explanations

    say "or" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    箫
    -0.25
    çļĦçľ¼åħī
    -0.25
    äu
    -0.24
    lâ
    -0.24
    ’ex
    -0.24
    akedown
    -0.24
     Ñĩа
    -0.24
    åĽº
    -0.24
    'ex
    -0.23
    è¦ģæĺ¯
    -0.23
    POSITIVE LOGITS
     Or
    0.67
    Or
    0.61
    .Or
    0.51
    ort
    0.48
    orth
    0.47
    ORT
    0.47
     OR
    0.46
     Orb
    0.46
     Ort
    0.45
     orch
    0.44
    Activations Density 0.007%

    No Known Activations