© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6717
    Prev
    Next
    INDEX
    Explanations

    installation and fitting services

    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
    éĻħ
    -0.09
    åĩĦ
    -0.09
    _compat
    -0.09
    åħľ
    -0.09
    ogle
    -0.09
    åĩ»
    -0.08
    ç»ĨåĪĨ
    -0.08
    æ±ľ
    -0.08
    æIJħ
    -0.08
    æijĦ
    -0.08
    POSITIVE LOGITS
    å®īè£ħ
    0.18
     installation
    0.15
     ìĦ¤ì¹ĺ
    0.14
    .install
    0.13
    æĹĦ
    0.13
    éĵºè®¾
    0.13
     install
    0.13
    installation
    0.12
    Installation
    0.12
     Installation
    0.11
    Activations Density 0.126%

    No Known Activations