© 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. 109069
    Prev
    Next
    INDEX
    Explanations

    while

    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
    花瓣
    -0.08
     xen
    -0.08
     BEN
    -0.07
    FileNotFoundException
    -0.07
     Toyota
    -0.07
    Ess
    -0.07
    Ṭ
    -0.07
    🤍
    -0.07
    لجنة
    -0.07
     Nit
    -0.07
    POSITIVE LOGITS
    评为
    0.07
     Vậy
    0.07
    ?\
    0.07
    ordo
    0.07
    ось
    0.07
    iah
    0.07
     יכול
    0.07
    江湖
    0.07
     phố
    0.06
     )(
    0.06
    Activations Density 0.016%

    No Known Activations