© 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. 2778
    Prev
    Next
    INDEX
    Explanations

    positive outlook

    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
    åĥ®
    -0.24
    追éĹ®
    -0.23
    éľĩæħij
    -0.23
    å«ĸ
    -0.22
    qua
    -0.21
    าร
    -0.21
    addons
    -0.21
    jax
    -0.21
    aceous
    -0.21
    äºĨä»ĸçļĦ
    -0.21
    POSITIVE LOGITS
     positively
    0.32
     positive
    0.30
    -positive
    0.30
     life
    0.28
    positive
    0.27
    çľĭå¾ħ
    0.27
     positivity
    0.26
     everyday
    0.26
     Positive
    0.26
     positives
    0.26
    Activations Density 0.013%

    No Known Activations