© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 129421
    Prev
    Next
    INDEX
    Explanations

    guessing games and clues

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bride
    -0.08
    胳膊
    -0.07
     NSLocalizedString
    -0.06
    ᅟ
    -0.06
    	cur
    -0.06
    小腿
    -0.06
    MBER
    -0.06
     queen
    -0.06
    ⛇
    -0.06
     parish
    -0.06
    POSITIVE LOGITS
    不低于
    0.08
     Dolphins
    0.07
     Spend
    0.07
    Ớ
    0.07
    研究中心
    0.07
     жизни
    0.07
     Contributor
    0.07
    管控
    0.07
     Fame
    0.07
    研发中心
    0.07
    Activations Density 0.181%

    No Known Activations