© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37967
    Prev
    Next
    INDEX
    Explanations

    Christmas Spectacular

    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
    æŁ³
    -0.12
    CHASE
    -0.11
    spath
    -0.10
    Orm
    -0.10
    eland
    -0.09
    æīĵæī«
    -0.09
    âĹ½
    -0.09
    çĶ
    -0.09
    饧
    -0.09
    agara
    -0.09
    POSITIVE LOGITS
    lob
    0.08
    aut
    0.08
    top
    0.08
    term
    0.08
    phen
    0.07
    ity
    0.07
    ism
    0.07
    nh
    0.07
    pos
    0.07
    ll
    0.07
    Activations Density 0.020%

    No Known Activations