© 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. 11-RESID-POST-AA
    11. 92660
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的确是
    -0.07
    对该
    -0.07
     élev
    -0.07
    	Register
    -0.07
     zipfile
    -0.07
     cómo
    -0.07
    ขยาย
    -0.07
    DAL
    -0.07
    为例
    -0.07
     uwagę
    -0.07
    POSITIVE LOGITS
     Fran
    0.07
     Desk
    0.06
     proactive
    0.06
    主动性
    0.06
    empor
    0.06
     disin
    0.06
    	int
    0.06
     прав
    0.06
    ncmp
    0.06
    .writerow
    0.06
    Activations Density 0.025%

    No Known Activations