© 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. 31229
    Prev
    Next
    INDEX
    Explanations

    pre-

    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
    olk
    -0.10
    æ·±å¤Ħ
    -0.09
    çĸ²
    -0.09
    leck
    -0.09
    rels
    -0.09
    黳
    -0.09
    ineTransform
    -0.09
    orts
    -0.09
    åĩĨæŶ
    -0.09
    ëĿ½
    -0.08
    POSITIVE LOGITS
    /pre
    0.13
    /post
    0.12
    (pre
    0.12
    lude
    0.12
    iminary
    0.10
    饷
    0.10
    åħĨ
    0.10
    centage
    0.10
    chè
    0.09
    conditions
    0.09
    Activations Density 0.230%

    No Known Activations