© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23688
    Prev
    Next
    INDEX
    Explanations

    Thomaston, Thomson, isa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ðŁı»
    -0.11
    ties
    -0.10
    abor
    -0.10
    çĵ£
    -0.10
    åĬŀäºĭå¤Ħ
    -0.09
    ×ķת
    -0.09
    ðŁı¼
    -0.09
    oko
    -0.09
    osit
    -0.09
    åĵ®
    -0.09
    POSITIVE LOGITS
    sWith
    0.14
    çĦ¶æĺ¯
    0.11
    swith
    0.10
    amp
    0.10
    ry
    0.09
    rax
    0.09
    ãģĹãģ¾ãģĦ
    0.09
    ãģ¾ãģĻãģĮ
    0.09
    _userdata
    0.09
    urator
    0.09
    Activations Density 0.149%

    No Known Activations