© 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. 129347
    Prev
    Next
    INDEX
    Explanations

    say "sh" words

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    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
    らず
    -0.07
    丫头
    -0.07
    卖场
    -0.07
     mosaic
    -0.07
    box
    -0.07
    جماع
    -0.07
     POP
    -0.06
    	elsif
    -0.06
    漫画
    -0.06
     enlarge
    -0.06
    POSITIVE LOGITS
    ights
    0.07
    เทรด
    0.07
    QS
    0.07
    Phones
    0.07
    cheduler
    0.07
    WE
    0.07
    운
    0.06
    nd
    0.06
    的伟大
    0.06
    ്
    0.06
    Activations Density 0.111%

    No Known Activations