© 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. 15-RESID-POST-AA
    11. 20852
    Prev
    Next
    INDEX
    Explanations

    server access and permissions

    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
     UITableView
    -0.07
     col
    -0.07
     phiếu
    -0.07
    摩托
    -0.07
    徼
    -0.07
     עשרות
    -0.07
     foundational
    -0.07
     Plasma
    -0.07
     Recon
    -0.07
    _loader
    -0.07
    POSITIVE LOGITS
    /examples
    0.08
    앴
    0.08
     Six
    0.07
     adulti
    0.07
    丧失
    0.07
     arb
    0.07
    看待
    0.07
    )a
    0.07
     Louise
    0.07
    educ
    0.07
    Activations Density 0.008%

    No Known Activations