© 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. 89093
    Prev
    Next
    INDEX
    Explanations

    feeling alone or isolated

    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
     redistributed
    -0.11
     redistrib
    -0.10
     Interr
    -0.10
    enu
    -0.09
     bored
    -0.09
    æĺ
    -0.09
     Econom
    -0.09
    afil
    -0.09
     unm
    -0.09
    _fwd
    -0.09
    POSITIVE LOGITS
     isolation
    0.28
     isolated
    0.26
     isol
    0.25
     secrecy
    0.24
     secretive
    0.22
    isol
    0.22
     isolate
    0.21
     Shame
    0.21
     conceal
    0.21
     shame
    0.19
    Activations Density 0.041%

    No Known Activations