© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59153
    Prev
    Next
    INDEX
    Explanations

    claims and statements

    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
     lar
    -0.10
    arat
    -0.10
    çŃĸ
    -0.09
     Conditions
    -0.09
    åĽŀåij³
    -0.09
    _REGS
    -0.09
    æĻĵå¾Ĺ
    -0.08
    xo
    -0.08
     respondent
    -0.08
    pee
    -0.08
    POSITIVE LOGITS
     claims
    0.25
     claim
    0.24
    声称
    0.21
    claims
    0.20
     CLAIM
    0.19
    claim
    0.18
     Claims
    0.18
     Claim
    0.18
     claiming
    0.17
    Claim
    0.17
    Activations Density 0.063%

    No Known Activations