© 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. 58184
    Prev
    Next
    INDEX
    Explanations

    suited for

    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
    ableObject
    -0.10
    able
    -0.09
    ationToken
    -0.09
    åIJİåı°
    -0.09
    çĵł
    -0.08
    son
    -0.08
    sem
    -0.08
    è¬ĩ
    -0.08
    asing
    -0.08
    .Misc
    -0.08
    POSITIVE LOGITS
    NESS
    0.11
    eness
    0.11
    ADER
    0.10
    ness
    0.10
    åıĪ好
    0.09
    ropri
    0.09
    TING
    0.09
    boro
    0.09
    人å±ħ
    0.09
    èĢĮåıĪ
    0.09
    Activations Density 0.012%

    No Known Activations