© 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. 16173
    Prev
    Next
    INDEX
    Explanations

    recruitment

    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
     NotImplemented
    -0.10
    è£ħ
    -0.09
     Hawth
    -0.09
    amic
    -0.09
    ibir
    -0.09
    ately
    -0.08
     abstract
    -0.08
     Stick
    -0.08
    -w
    -0.08
     Laur
    -0.08
    POSITIVE LOGITS
    /en
    0.12
     recruitment
    0.11
     into
    0.11
     recruiting
    0.11
     Recruitment
    0.11
     talent
    0.11
     recruit
    0.11
     Recru
    0.11
     recruits
    0.11
    /rec
    0.10
    Activations Density 0.062%

    No Known Activations