© 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. 7293
    Prev
    Next
    INDEX
    Explanations

    purchase and its consequences

    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
    ities
    -0.13
    à¹Į
    -0.09
    иÑĢование
    -0.09
    å½Ģ
    -0.09
    merc
    -0.09
    è¾ľè´Ł
    -0.09
    æµĵæµĵçļĦ
    -0.09
    IOS
    -0.09
    ues
    -0.09
    ãģĦãĤĭ
    -0.09
    POSITIVE LOGITS
    able
    0.16
    ABLE
    0.14
    ables
    0.14
    OrCreate
    0.11
    赦
    0.09
    abler
    0.09
    ably
    0.09
    ability
    0.09
    oire
    0.09
    OTT
    0.08
    Activations Density 0.016%

    No Known Activations