© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4612
    Prev
    Next
    INDEX
    Explanations

    presence of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eh
    -0.09
    URN
    -0.09
    ltk
    -0.08
    ä¸įèµ·
    -0.08
    PRI
    -0.08
     Incoming
    -0.08
    鼶
    -0.08
     PRI
    -0.08
    olvers
    -0.08
     Benson
    -0.08
    POSITIVE LOGITS
     presence
    0.33
    presence
    0.28
     Presence
    0.27
    Presence
    0.27
    çļĦåŃĺåľ¨
    0.25
    _presence
    0.23
     presença
    0.23
     présence
    0.23
     налиÑĩие
    0.20
    身影
    0.16
    Activations Density 0.067%

    No Known Activations