© 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. 128720
    Prev
    Next
    INDEX
    Explanations

    inherit

    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_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
    刿
    -0.08
    ཚ
    -0.07
    	ob
    -0.07
    רכת
    -0.07
    三家
    -0.07
    荇
    -0.07
     spur
    -0.07
    PostMapping
    -0.07
    ጃ
    -0.07
    usion
    -0.07
    POSITIVE LOGITS
     Supreme
    0.08
     algebra
    0.07
     goals
    0.07
    )+"
    0.07
    REAL
    0.07
     SSL
    0.07
    我们认为
    0.07
     schedules
    0.07
     Ал
    0.07
    蓝
    0.07
    Activations Density 0.028%

    No Known Activations