© 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. 18895
    Prev
    Next
    INDEX
    Explanations

    surreal, cerebral, existentialisms

    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
    OrCreate
    -0.11
    æģķ
    -0.09
    jee
    -0.09
    ÑĥÑĩа
    -0.08
    æīĢ以说
    -0.08
    RATE
    -0.08
    lain
    -0.08
    èĢ
    -0.08
    ophilia
    -0.08
    noon
    -0.08
    POSITIVE LOGITS
    istic
    0.16
    istically
    0.16
    ists
    0.14
    ism
    0.13
    主ä¹ī
    0.13
    ìłģìľ¼ë¡ľ
    0.11
    ISTIC
    0.11
    ìłģìĿ¸
    0.11
    -minded
    0.10
    å·©
    0.10
    Activations Density 0.008%

    No Known Activations