© 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. 27837
    Prev
    Next
    INDEX
    Explanations

    converting text or data types

    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
    ening
    -0.12
    ×ķת
    -0.11
    hood
    -0.10
    ForResult
    -0.10
    istic
    -0.09
    /her
    -0.09
    erg
    -0.09
    urity
    -0.09
    adier
    -0.09
    inger
    -0.09
    POSITIVE LOGITS
    idor
    0.14
    itore
    0.14
    ible
    0.10
    IBLE
    0.10
    isseur
    0.09
    icles
    0.09
     дÑĥÑħ
    0.09
    _into
    0.09
    ICLE
    0.09
    .DeserializeObject
    0.09
    Activations Density 0.086%

    No Known Activations