© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 110732
    Prev
    Next
    INDEX
    Explanations

    "net

    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
    .WRITE
    -0.07
     których
    -0.07
    走到
    -0.07
    blast
    -0.07
     CreateUser
    -0.07
     Kits
    -0.07
    良
    -0.06
    _EC
    -0.06
     ado
    -0.06
    表决
    -0.06
    POSITIVE LOGITS
    (ref
    0.07
     frontend
    0.07
     pond
    0.07
    美国
    0.06
     sneakers
    0.06
     demographics
    0.06
    确切
    0.06
    ของเรา
    0.06
     JFrame
    0.06
    Cal
    0.06
    Activations Density 0.001%

    No Known Activations