© 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. 52637
    Prev
    Next
    INDEX
    Explanations

    after I

    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
    æī¹åıijå¸Ĥåľº
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    ä½ķå¤Ħ
    -0.08
    ipmap
    -0.08
    urse
    -0.08
    affle
    -0.08
    bie
    -0.08
    æİĴè¡Įæ¦ľ
    -0.08
    åĢĻéĢī人
    -0.08
    ihu
    -0.08
    POSITIVE LOGITS
    noon
    0.10
    ward
    0.10
    orative
    0.09
    WARDS
    0.09
    dem
    0.09
    esa
    0.09
    wards
    0.09
    å½ĵçĦ¶æĺ¯
    0.09
    word
    0.09
    åĴ¨
    0.08
    Activations Density 0.032%

    No Known Activations