© 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. 27187
    Prev
    Next
    INDEX
    Explanations

    Jake, Kathy, megan, stephanie, kathy, jake, athy, kathy, namanda

    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
    è¿Ļæł·æīįèĥ½
    -0.11
    èĩ¾
    -0.10
    ately
    -0.10
    craft
    -0.10
    olate
    -0.10
    beat
    -0.09
    erate
    -0.09
    pins
    -0.09
    zelf
    -0.09
    ault
    -0.08
    POSITIVE LOGITS
    çĿ¬
    0.12
    ëģĶ
    0.10
    ðŁı»
    0.10
    ieves
    0.10
    orra
    0.09
    rust
    0.09
    sonian
    0.09
    ÑĢам
    0.09
    <?,
    0.09
    ãģıãĤĭ
    0.09
    Activations Density 0.051%

    No Known Activations