© 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. 39314
    Prev
    Next
    INDEX
    Explanations

    venue and related locations

    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
    ench
    -0.10
    ophone
    -0.10
    board
    -0.08
    ึà¸ģ
    -0.08
    éķľå¤´
    -0.08
    ë§Ŀ
    -0.08
    å¢ĥçķĮ
    -0.08
    enza
    -0.08
    reno
    -0.08
    aceous
    -0.08
    POSITIVE LOGITS
    stral
    0.11
    åħ«åŃĹ
    0.10
    OfBirth
    0.09
    -neutral
    0.09
    iers
    0.09
    forth
    0.09
    ned
    0.09
    éĺĹ
    0.09
    ibre
    0.09
    zu
    0.09
    Activations Density 0.005%

    No Known Activations