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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77296
    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
    衾
    -0.07
    珖
    -0.07
     structures
    -0.07
    嵩
    -0.07
    罶
    -0.07
    _rules
    -0.07
    cję
    -0.06
    ǣ
    -0.06
    ilogy
    -0.06
    ｔ
    -0.06
    POSITIVE LOGITS
    乙
    0.07
    來自
    0.07
     WIDTH
    0.07
    已
    0.07
     ?:
    0.07
    HorizontalAlignment
    0.07
    EXTERN
    0.06
    	hs
    0.06
    Login
    0.06
     ,-
    0.06
    Activations Density 0.031%

    No Known Activations