© 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. 23486
    Prev
    Next
    INDEX
    Explanations

    body parts or containers

    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
    anko
    -0.12
    æĴ¥
    -0.09
    åij½
    -0.09
    hte
    -0.09
    çĽĨåľ°
    -0.09
    çĥŁçģ«
    -0.09
    å®ħ
    -0.09
    _disk
    -0.09
     Anth
    -0.08
    bud
    -0.08
    POSITIVE LOGITS
    åľº
    0.09
    åıĹæįŁ
    0.09
    æŃ£æĸĩ
    0.09
     body
    0.09
    -content
    0.08
     доÑģÑĤ
    0.08
    èĩĢ
    0.08
    çĻ»
    0.08
    _RS
    0.08
    çŀĦ
    0.08
    Activations Density 0.142%

    No Known Activations