© 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. 33865
    Prev
    Next
    INDEX
    Explanations

    plus addition or continuation

    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
     nevertheless
    -0.12
     nonetheless
    -0.10
    å¹»
    -0.10
    以èĩ´
    -0.09
    soever
    -0.09
    atsu
    -0.09
    便åı¯
    -0.09
    ä¹Łéļıä¹ĭ
    -0.09
    åħ·ä½ĵåĨħ容
    -0.09
    bo
    -0.08
    POSITIVE LOGITS
    å½ĵæĪij
    0.09
    ismatic
    0.08
    ammen
    0.08
     оÑĢи
    0.08
    หมà¸Ķ
    0.08
    ulk
    0.08
    /OR
    0.08
    ilinear
    0.08
    EndInit
    0.08
    pet
    0.08
    Activations Density 0.011%

    No Known Activations