© 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. 31722
    Prev
    Next
    INDEX
    Explanations

    accessory and related items

    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
    /or
    -0.11
    ish
    -0.09
    nings
    -0.09
    inals
    -0.09
    еж
    -0.09
    èĭķ
    -0.09
    nie
    -0.09
    rise
    -0.08
    enance
    -0.08
     ê°Ģì§Ģ
    -0.08
    POSITIVE LOGITS
    ÑĤÑĮ
    0.09
    ivity
    0.09
    èĩªå¦Ĥ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ¬
    0.09
    lemn
    0.09
    ment
    0.09
    AndView
    0.09
     ByVal
    0.08
    manda
    0.08
    Activations Density 0.005%

    No Known Activations