© 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. 17630
    Prev
    Next
    INDEX
    Explanations

    current/concurrent actions or states

    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
    çĶij
    -0.09
    屿
    -0.09
    istic
    -0.09
    екÑĤоÑĢ
    -0.08
    _CTL
    -0.08
    çĤĢ
    -0.08
    ored
    -0.08
    äºĨä¸Ģä¸ĭ
    -0.08
    çĵ¶
    -0.08
    rts
    -0.08
    POSITIVE LOGITS
    ../../../
    0.14
    edly
    0.09
    istory
    0.08
    erer
    0.08
    laps
    0.08
    iously
    0.08
    STIT
    0.08
    illus
    0.08
    olly
    0.08
    elor
    0.08
    Activations Density 0.026%

    No Known Activations