© 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. 76108
    Prev
    Next
    INDEX
    Explanations

    Python code using URL

    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
     Lam
    -0.08
    Its
    -0.08
    蕰
    -0.07
     foe
    -0.07
    督办
    -0.07
     alcuni
    -0.07
    élé
    -0.07
    傀
    -0.07
    🌄
    -0.07
    April
    -0.07
    POSITIVE LOGITS
    转移
    0.07
    (Y
    0.07
    /de
    0.07
     NE
    0.07
    collector
    0.07
    �
    0.07
    欲しい
    0.07
     }//
    0.07
    \',
    0.07
    质
    0.07
    Activations Density 0.002%

    No Known Activations