© 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. 86796
    Prev
    Next
    INDEX
    Explanations

    "n't" contractions

    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
     facet
    -0.07
    Listing
    -0.07
     собран
    -0.07
    �
    -0.07
     newsletters
    -0.07
    Joe
    -0.07
     vast
    -0.07
     Alley
    -0.07
    .node
    -0.06
    (function
    -0.06
    POSITIVE LOGITS
     Preferred
    0.08
    带队
    0.07
    臌
    0.07
     заболевания
    0.07
     의
    0.07
    于
    0.07
     управления
    0.07
    овым
    0.07
    够
    0.07
     nadzieję
    0.07
    Activations Density 0.014%

    No Known Activations