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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 63559
    Prev
    Next
    INDEX
    Explanations

    stiffness

    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
    lineEdit
    -0.08
    \Web
    -0.07
    -details
    -0.07
    ZE
    -0.07
     rentals
    -0.07
     beide
    -0.07
     WebGL
    -0.07
    rending
    -0.07
    tributes
    -0.06
    ads
    -0.06
    POSITIVE LOGITS
    -conscious
    0.07
    抓
    0.07
    蟠
    0.07
    .Attach
    0.07
    Clar
    0.07
    []>↵
    0.07
    ◼
    0.06
    邻居
    0.06
     Earl
    0.06
    .CONT
    0.06
    Activations Density 0.006%

    No Known Activations