© 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. 2170
    Prev
    Next
    INDEX
    Explanations

    search results

    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
     transitioning
    -0.25
    èĦĶ
    -0.25
    spoken
    -0.24
    ·»
    -0.24
     hormones
    -0.23
    WriteBarrier
    -0.22
    CloseOperation
    -0.22
    (EXPR
    -0.22
    ronics
    -0.22
    .Ar
    -0.22
    POSITIVE LOGITS
    符åIJĪæĿ¡ä»¶
    0.43
    æ£Ģç´¢
    0.43
    ç»ĵæŀľ
    0.43
     results
    0.41
    æIJľç´¢
    0.40
    çļĦç»ĵæŀľ
    0.38
    æī¾åĪ°äºĨ
    0.36
    çŃĽéĢī
    0.36
     retrieved
    0.36
    ç»ĵæŀľæĺ¾ç¤º
    0.36
    Activations Density 0.178%

    No Known Activations