© 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. 63403
    Prev
    Next
    INDEX
    Explanations

    company money

    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
     underground
    -0.08
     ent
    -0.08
    .ent
    -0.08
    ä¸Ģæī¹
    -0.08
    å²Ĺ
    -0.08
    产åĩº
    -0.08
    仫
    -0.08
    moid
    -0.08
    ajar
    -0.08
    å¸ĪèĮĥ
    -0.07
    POSITIVE LOGITS
    èĪªè¡Į
    0.16
    èĪ·
    0.14
    游èīĩ
    0.14
    èĪ¹èĪ¶
    0.13
    èĪµ
    0.13
    æ¡ħ
    0.12
    èĪ¹
    0.11
    èĪ¹ä¸Ĭ
    0.11
     yacht
    0.11
    èīĩ
    0.11
    Activations Density 0.072%

    No Known Activations