© 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. 6920
    Prev
    Next
    INDEX
    Explanations

    jail and prison

    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
    æ³¼
    -0.09
    ç¼Ĵ
    -0.09
    /devices
    -0.08
    _ONCE
    -0.08
    abilité
    -0.08
    åħ¬ç¤º
    -0.08
    iego
    -0.08
    uchi
    -0.08
    åĩŃä»Ģä¹Ī
    -0.08
    æĬ¥åijĬ
    -0.08
    POSITIVE LOGITS
    çĽijçĭ±
    0.19
     prison
    0.18
    çĭ±
    0.17
     jail
    0.16
    åĽļ
    0.16
    æĭĺçķĻ
    0.15
     Prison
    0.14
     Jail
    0.14
    çįĦ
    0.13
     prisons
    0.13
    Activations Density 0.187%

    No Known Activations