© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    ICD codes

    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
     THINK
    -0.07
    Written
    -0.07
    _qp
    -0.07
     trước
    -0.07
    correct
    -0.06
    spi
    -0.06
    ✾
    -0.06
    thesis
    -0.06
    איר
    -0.06
    @GeneratedValue
    -0.06
    POSITIVE LOGITS
     regularization
    0.09
    宁
    0.07
     lamb
    0.07
     תוכנ
    0.07
    (lat
    0.07
    MB
    0.07
     lique
    0.07
    长期
    0.07
     BAT
    0.07
    .OrderBy
    0.07
    Activations Density 0.001%

    No Known Activations