© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 126847
    Prev
    Next
    INDEX
    Explanations

    realistic

    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
     school
    -0.09
     точки
    -0.08
    职业教育
    -0.08
     started
    -0.07
     reaching
    -0.07
    ڸ
    -0.07
     llegar
    -0.07
    (off
    -0.07
    ի
    -0.06
     começou
    -0.06
    POSITIVE LOGITS
    _THREADS
    0.07
    	SET
    0.07
    Inject
    0.07
    公关
    0.07
    /'+
    0.07
     Grant
    0.07
    生育
    0.07
    illus
    0.07
    apist
    0.07
     Paradise
    0.07
    Activations Density 0.089%

    No Known Activations