© 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. 33009
    Prev
    Next
    INDEX
    Explanations

    woodland or WLAN

    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
    hetto
    -0.09
    elia
    -0.09
     Swamp
    -0.09
    ä¹IJè§Ĥ
    -0.08
    件
    -0.08
    ickness
    -0.08
    ramer
    -0.08
     bá»ı
    -0.08
    rame
    -0.08
    linger
    -0.08
    POSITIVE LOGITS
     обÑĢазом
    0.09
    ANNER
    0.09
     Lad
    0.09
    rab
    0.09
    tör
    0.09
    çĭİ
    0.09
    aks
    0.09
    رش
    0.09
    kos
    0.09
    -addon
    0.09
    Activations Density 0.007%

    No Known Activations