© 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 EvalsExportsinterp-engineNEWAPI 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. 67151
    Prev
    Next
    INDEX
    Explanations

    legal references

    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
     wired
    -0.08
    _<
    -0.07
     racks
    -0.07
    ছ
    -0.06
    延续
    -0.06
    zer
    -0.06
    fell
    -0.06
     suburbs
    -0.06
    _uid
    -0.06
    ࡒ
    -0.06
    POSITIVE LOGITS
    vore
    0.08
     Learned
    0.07
     gỗ
    0.07
    Ast
    0.07
    .vn
    0.07
    /orders
    0.07
    蟊
    0.07
     เม
    0.07
    𝐺
    0.07
    ]init
    0.07
    Activations Density 0.009%

    No Known Activations