© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28439
    Prev
    Next
    INDEX
    Explanations

    ate followed by ch or blanch

    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
    ¡°
    -0.10
    lator
    -0.09
    bef
    -0.08
    ookie
    -0.08
    elles
    -0.08
    riet
    -0.08
    815
    -0.08
    .ov
    -0.08
    515
    -0.08
     stap
    -0.08
    POSITIVE LOGITS
    fully
    0.19
    igner
    0.12
    pillar
    0.12
    lescope
    0.11
    ways
    0.10
    sters
    0.10
    water
    0.10
    payer
    0.10
    chin
    0.10
    rox
    0.10
    Activations Density 0.084%

    No Known Activations