© 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. 3285
    Prev
    Next
    INDEX
    Explanations

    mind control, mindshift, mind fit

    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
    ity
    -0.11
    åĬ²
    -0.10
    iom
    -0.09
    eer
    -0.09
    çĦ¶
    -0.09
    çİ°è´§
    -0.08
    ish
    -0.08
    ists
    -0.08
    ile
    -0.08
    atch
    -0.08
    POSITIVE LOGITS
    fuck
    0.14
    lessly
    0.13
    ustry
    0.12
    lessness
    0.11
    stem
    0.11
    shake
    0.11
    ê»ı
    0.11
    edly
    0.11
    less
    0.11
    fully
    0.11
    Activations Density 0.021%

    No Known Activations