© 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. 62693
    Prev
    Next
    INDEX
    Explanations

    promising strategies or approaches

    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
    uated
    -0.09
    éŃħ
    -0.09
    robe
    -0.08
    arend
    -0.08
    agan
    -0.08
    uate
    -0.08
    uation
    -0.08
    istra
    -0.08
    ÑĢаÑģ
    -0.08
    éŃħåĬĽ
    -0.08
    POSITIVE LOGITS
    ably
    0.12
    åĭĥåĭĥ
    0.12
     hẹn
    0.12
    ente
    0.11
     Ñģобой
    0.10
    keiten
    0.10
    веÑī
    0.10
    å·²ä¹ħçļĦ
    0.10
    ollar
    0.10
    edio
    0.10
    Activations Density 0.010%

    No Known Activations