© 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. 88736
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation

    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
     clutch
    -0.08
    cil
    -0.07
    lip
    -0.07
    asher
    -0.07
    sei
    -0.07
    ì§
    -0.07
     bedside
    -0.07
    .LoggerFactory
    -0.07
     nog
    -0.07
    modal
    -0.07
    POSITIVE LOGITS
    pz
    0.10
     squeeze
    0.09
     hug
    0.09
    .GenerationType
    0.09
    msp
    0.09
     Padding
    0.08
    .JsonProperty
    0.08
     squeezing
    0.08
     Whisper
    0.08
     valu
    0.08
    Activations Density 1.984%

    No Known Activations