© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    gastropod mollusks and snails with shells

    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
    fir
    -0.28
    çĩĥ
    -0.26
    çĩĥæ²¹
    -0.25
    æ¹į
    -0.25
    rze
    -0.24
    çĩĥçĥ§
    -0.24
     fir
    -0.24
    åİŁæ²¹
    -0.24
     fiery
    -0.24
    æĢ»éĺŁ
    -0.23
    POSITIVE LOGITS
    è´Ŀ壳
    0.35
    èľĹ
    0.35
    壳
    0.35
     moll
    0.32
     shells
    0.32
     shell
    0.30
    (shell
    0.29
     turtles
    0.28
    -shell
    0.28
    èĽ³
    0.28
    Activations Density 0.095%

    No Known Activations