© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 74867
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .If
    -0.08
     comedian
    -0.08
     AF
    -0.07
    ถาม
    -0.07
    Ask
    -0.07
    ...)↵
    -0.07
    	Query
    -0.07
     insists
    -0.07
    老爷
    -0.07
    daf
    -0.07
    POSITIVE LOGITS
     Bur
    0.07
    _highlight
    0.06
    港区
    0.06
    埆
    0.06
    账
    0.06
    נע
    0.06
    (\'
    0.06
     نتيجة
    0.06
     bland
    0.06
    ﲬ
    0.06
    Activations Density 0.015%

    No Known Activations