© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3114
    Prev
    Next
    INDEX
    Explanations

    softness, softening, or soft materials

    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
    大äºĭ
    -0.27
     Locker
    -0.22
     Cold
    -0.22
    çĤ«èĢĢ
    -0.22
     spawning
    -0.21
    佯
    -0.21
    éĢŀ
    -0.21
    SPATH
    -0.20
    æįķ
    -0.20
    åĨ·åĨ·
    -0.20
    POSITIVE LOGITS
    ening
    0.33
     má»ģm
    0.28
     mại
    0.28
    ness
    0.26
    eners
    0.26
    -hearted
    0.26
    åīĤ
    0.26
    -bodied
    0.25
    ç»Ĩèħ»
    0.25
     cushions
    0.24
    Activations Density 0.007%

    No Known Activations