© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111657
    Prev
    Next
    INDEX
    Explanations

    confession or anonymous sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     Baghd
    -0.09
    pps
    -0.09
     Pulitzer
    -0.08
     cookbook
    -0.08
     Anc
    -0.08
     Fancy
    -0.08
     rud
    -0.08
     docs
    -0.08
     Sword
    -0.08
     Instructor
    -0.07
    POSITIVE LOGITS
     confession
    0.24
     confess
    0.23
     anonymously
    0.21
     anonymous
    0.20
     conf
    0.18
     confessed
    0.17
     anonym
    0.17
     confidential
    0.17
     Anonymous
    0.17
     Conf
    0.16
    Activations Density 0.030%

    No Known Activations