© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90402
    Prev
    Next
    INDEX
    Explanations

    except, including

    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
    linger
    -0.12
     partly
    -0.12
     truncate
    -0.10
    =min
    -0.10
     trunc
    -0.10
     dob
    -0.10
    eva
    -0.10
    (Have
    -0.10
     ALWAYS
    -0.10
    lov
    -0.09
    POSITIVE LOGITS
     except
    0.19
    —including
    0.17
    except
    0.15
     including
    0.15
     Except
    0.15
    Except
    0.15
     Including
    0.15
    Including
    0.13
     INCLUDING
    0.12
    —from
    0.12
    Activations Density 0.249%

    No Known Activations