© 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. 19-RESID-POST-AA
    11. 75719
    Prev
    Next
    INDEX
    Explanations

    Intimal hyperplasia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spre
    -0.07
    了很久
    -0.07
     presents
    -0.07
    appa
    -0.07
     FVector
    -0.07
     인정
    -0.07
    aptors
    -0.07
     kvp
    -0.07
     timeout
    -0.06
    [L
    -0.06
    POSITIVE LOGITS
     indexer
    0.08
     Closed
    0.07
     talented
    0.07
     рейтинг
    0.07
    sequence
    0.07
     manufacturers
    0.07
    مبادئ
    0.07
     arm
    0.06
     그래서
    0.06
    ilent
    0.06
    Activations Density 0.001%

    No Known Activations