© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36424
    Prev
    Next
    INDEX
    Explanations

    names starting with Lil or Lily

    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
    bidden
    -0.10
    lace
    -0.10
    ees
    -0.09
    eated
    -0.09
    yard
    -0.09
    宿
    -0.09
    ease
    -0.09
    деÑģÑıÑĤ
    -0.08
    èĽ¤
    -0.08
    een
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.10
    ient
    0.10
    åħĴ
    0.10
    éĻ¤æѤä¹ĭå¤ĸ
    0.09
    çīµå¼ķ
    0.09
    hood
    0.09
    atures
    0.09
    åīįæīĢ
    0.09
    ipop
    0.09
    æ²¹çĶ°
    0.09
    Activations Density 0.007%

    No Known Activations