© 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. 22155
    Prev
    Next
    INDEX
    Explanations

    clover street or honey

    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
    subst
    -0.09
    é¡¿
    -0.09
    aines
    -0.09
    oger
    -0.09
    æĵİ
    -0.08
    _RANDOM
    -0.08
    urv
    -0.08
    好似
    -0.08
    slash
    -0.08
    æĶ¶è´¹æłĩåĩĨ
    -0.08
    POSITIVE LOGITS
    ness
    0.12
    渥
    0.11
    dale
    0.11
    mani
    0.10
    leaf
    0.10
    ç¿»
    0.09
    matic
    0.09
    اش
    0.09
    iable
    0.09
    land
    0.09
    Activations Density 0.005%

    No Known Activations