© 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. 39614
    Prev
    Next
    INDEX
    Explanations

    renheit, chmidt, raries

    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
    iful
    -0.10
    ler
    -0.09
    illis
    -0.09
    itional
    -0.09
    ousel
    -0.08
    lify
    -0.08
    ller
    -0.08
    _allocation
    -0.08
    orial
    -0.08
     laps
    -0.08
    POSITIVE LOGITS
    andro
    0.12
    arity
    0.11
    RARY
    0.10
    itud
    0.10
    gren
    0.10
    hammer
    0.10
    raries
    0.09
    undry
    0.09
    UNCH
    0.09
    coln
    0.09
    Activations Density 0.758%

    No Known Activations