© 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. 43274
    Prev
    Next
    INDEX
    Explanations

    oral

    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
     paz
    -0.29
     chatt
    -0.29
    mare
    -0.28
    chia
    -0.28
    Å¡t
    -0.27
    å¤ļæĸ¹
    -0.27
    BCM
    -0.26
    alement
    -0.26
    æ¸ļ
    -0.26
     pisc
    -0.25
    POSITIVE LOGITS
    oral
    0.41
     oral
    0.33
     coll
    0.33
     bu
    0.30
     Oral
    0.28
    Coll
    0.28
    ollo
    0.27
    Bu
    0.27
    _coll
    0.27
     orally
    0.27
    Activations Density 0.003%

    No Known Activations