© 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. 55146
    Prev
    Next
    INDEX
    Explanations

    not perfect

    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
    lasses
    -0.11
    åı¸
    -0.10
    .JsonProperty
    -0.09
     recur
    -0.08
    üss
    -0.08
    adf
    -0.08
    æķ£
    -0.08
    elor
    -0.08
    lect
    -0.08
    æ·¦
    -0.08
    POSITIVE LOGITS
    å®Įç¾İ
    0.22
    å®Įç¾İçļĦ
    0.18
     perfection
    0.18
     perfect
    0.17
    perfect
    0.15
     Perfect
    0.14
    å®ĮåĸĦ
    0.14
    Perfect
    0.13
     imperfect
    0.13
    çIJĨæĥ³
    0.12
    Activations Density 0.057%

    No Known Activations