© 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. 58605
    Prev
    Next
    INDEX
    Explanations

    planning and future actions

    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
    åŃº
    -0.09
    ç¡Ŀ
    -0.09
    èĢģå¸ĪçļĦ
    -0.09
    UC
    -0.08
    uci
    -0.08
     Cra
    -0.08
    oming
    -0.08
    ¹
    -0.08
    eya
    -0.08
    çĽijçĿ£
    -0.08
    POSITIVE LOGITS
     planning
    0.11
    计åĪĴ
    0.11
    çŃĸåĪĴ
    0.11
    è§ĦåĪĴ
    0.11
    æķĻæ¡Ī
    0.11
     Plans
    0.10
     plans
    0.10
    åĪĺæµ·
    0.10
    è¨ĪåĬĥ
    0.10
    è¦ıåĬĥ
    0.10
    Activations Density 0.040%

    No Known Activations