© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21857
    Prev
    Next
    INDEX
    Explanations

    arn... followed by certain endings

    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
    ../../../
    -0.12
    ties
    -0.11
    ided
    -0.09
    gings
    -0.09
    èĩªå¦Ĥ
    -0.09
    ðŁı¾
    -0.09
    ../
    -0.09
    ðŁı¼
    -0.09
    chie
    -0.09
    ãģĤãģ¾ãĤĬ
    -0.09
    POSITIVE LOGITS
    side
    0.13
    ival
    0.11
    stead
    0.10
    alley
    0.10
    wright
    0.10
    éĻħ
    0.10
    ells
    0.09
    egative
    0.09
    ingly
    0.09
    arine
    0.09
    Activations Density 0.085%

    No Known Activations