© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1715
    Prev
    Next
    INDEX
    Explanations

    crumb or crumble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    汩
    -0.24
    ä»Ĺ
    -0.23
    _STANDARD
    -0.22
    åģĥ
    -0.21
    _many
    -0.21
    襦
    -0.20
    å¸ĪèĮĥ大åѦ
    -0.20
    itudes
    -0.20
     даннÑĭй
    -0.20
    riend
    -0.20
    POSITIVE LOGITS
    ll
    0.23
    Fel
    0.22
    enc
    0.22
     gran
    0.22
    stype
    0.21
    åĥı
    0.21
    æĤī
    0.21
    wise
    0.21
     representation
    0.21
    lessly
    0.20
    Activations Density 0.001%

    No Known Activations