© 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. 27378
    Prev
    Next
    INDEX
    Explanations

    password strings

    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
     fines
    -0.08
    ->↵
    -0.06
     misd
    -0.06
     MPU
    -0.06
     OTP
    -0.06
     penny
    -0.06
     Humb
    -0.06
    leo
    -0.05
    (Return
    -0.05
     CPF
    -0.05
    POSITIVE LOGITS
    _$_
    0.15
    Я
    0.14
    #!
    0.13
    inati
    0.13
    rå
    0.13
    £
    0.13
    Tri
    0.13
    оÐ
    0.13
    $o
    0.13
    @
    0.12
    Activations Density 0.178%

    No Known Activations