© 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. 2326
    Prev
    Next
    INDEX
    Explanations

    report abuse and flag content

    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
    åħħåĪĨä½ĵçİ°
    -0.21
    åij¨å¹´
    -0.21
     Mason
    -0.21
    è§ģè¯Ĩ
    -0.21
    named
    -0.21
     Omn
    -0.21
     EAR
    -0.20
     dynamic
    -0.20
    amarin
    -0.20
    æIJŀå¾Ĺ
    -0.20
    POSITIVE LOGITS
     spam
    0.29
    å±ŀå®ŀ
    0.28
     Spam
    0.28
    åŀĥåľ¾
    0.28
    .Flag
    0.27
     polite
    0.27
    çIJĨçĶ±
    0.27
     flagged
    0.26
    _reason
    0.26
    è¿Ŀè§Ħ
    0.26
    Activations Density 0.010%

    No Known Activations