© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1426
    Prev
    Next
    INDEX
    Explanations

    life and death decisions

    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
     Elim
    -0.25
    bras
    -0.24
    simp
    -0.24
    elim
    -0.23
    }//
    -0.23
     naturally
    -0.23
     Latest
    -0.22
    ëłĮ
    -0.21
    è°±
    -0.21
    ERIC
    -0.21
    POSITIVE LOGITS
     crucial
    0.44
    äºĭåħ³
    0.42
    èĩ³åħ³éĩįè¦ģ
    0.42
    æĪIJè´¥
    0.42
    åħ³ä¹İ
    0.42
    æķijåij½
    0.41
    èĥ½åIJ¦
    0.40
    çĶŁæŃ»
    0.39
    èĩ³åħ³
    0.39
    éĿŀ常éĩįè¦ģ
    0.38
    Activations Density 0.246%

    No Known Activations