© 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. 49247
    Prev
    Next
    INDEX
    Explanations

    polls and voting

    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
     вÑĭпол
    -0.10
    å«Ĥ
    -0.08
    åİļéĩį
    -0.08
     Fant
    -0.08
    解éĻ¤
    -0.07
    apo
    -0.07
    нÑĮ
    -0.07
    å·§
    -0.07
     observ
    -0.07
     Milit
    -0.07
    POSITIVE LOGITS
    æĬķ票
    0.23
     votes
    0.17
     vote
    0.17
    Vote
    0.17
     poll
    0.17
    poll
    0.16
     voting
    0.16
    表åĨ³
    0.16
     polls
    0.15
     Vote
    0.15
    Activations Density 0.040%

    No Known Activations