© 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. 57579
    Prev
    Next
    INDEX
    Explanations

    subject to license or terms

    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
    ìį¨
    -0.10
    oad
    -0.09
    aday
    -0.09
    wright
    -0.09
    IMUM
    -0.09
    åĽŀäºĭ
    -0.08
    thers
    -0.08
    ÑģÑĤÑĢа
    -0.08
    umph
    -0.08
    orte
    -0.08
    POSITIVE LOGITS
    ively
    0.17
    ivities
    0.16
    ivity
    0.15
    ivism
    0.12
    ive
    0.12
     Grinder
    0.12
    iveness
    0.12
    ably
    0.11
    ility
    0.10
    å¢ŀéķ¿çİĩ
    0.10
    Activations Density 0.055%

    No Known Activations