© 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. 57784
    Prev
    Next
    INDEX
    Explanations

    reform

    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
    -0.09
    åħ¨åijĺ
    -0.09
    _alive
    -0.09
    aneous
    -0.09
    ancer
    -0.09
    mos
    -0.08
    hole
    -0.08
     Imam
    -0.08
    ı
    -0.08
    dro
    -0.08
    POSITIVE LOGITS
    ä¸İåıijå±ķ
    0.13
    éĶ¹
    0.10
    leur
    0.10
    atted
    0.10
    èĢħçļĦ
    0.10
    atters
    0.10
    å·¥ä½ľä½ľé£İ
    0.09
    åĬĽåº¦
    0.09
    alted
    0.09
    ersh
    0.09
    Activations Density 0.010%

    No Known Activations