© 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. 30049
    Prev
    Next
    INDEX
    Explanations

    psychotherapy, analysis, therapists

    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
    iping
    -0.10
    å®Ī
    -0.09
    çĥ¦
    -0.09
    SystemService
    -0.09
    éĺ²æݧ
    -0.08
    æĦŁåĬ¨
    -0.08
    azon
    -0.08
    æīįåıijçİ°
    -0.08
    èĨ³
    -0.08
    heck
    -0.08
    POSITIVE LOGITS
    геÑĢ
    0.09
    磶
    0.08
     Trustees
    0.08
    æѦæŀĹ
    0.08
    .Scope
    0.08
    /ajax
    0.08
    渣
    0.08
    lando
    0.08
    æħ¶
    0.08
    COOKIE
    0.08
    Activations Density 0.042%

    No Known Activations