© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6212
    Prev
    Next
    INDEX
    Explanations

    legal texts

    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
     influx
    -0.08
     대해서
    -0.08
     siêu
    -0.07
     punitive
    -0.07
    袗
    -0.07
    話し
    -0.07
    𫠆
    -0.07
     unser
    -0.07
    ness
    -0.07
    ско
    -0.06
    POSITIVE LOGITS
    =_('
    0.07
     IMPLEMENT
    0.07
     Neuroscience
    0.07
    aths
    0.07
     Wells
    0.07
    要做到
    0.07
    Official
    0.07
     bleed
    0.07
    'D
    0.06
    Allowed
    0.06
    Activations Density 0.343%

    No Known Activations