© 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. 43019
    Prev
    Next
    INDEX
    Explanations

    2

    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
     bật
    -0.07
    /prom
    -0.07
     hoy
    -0.07
     Term
    -0.07
    ۽
    -0.07
    _EMP
    -0.07
     العن
    -0.06
    rün
    -0.06
     horm
    -0.06
     inspire
    -0.06
    POSITIVE LOGITS
    相关信息
    0.08
     delicate
    0.07
     ReSharper
    0.07
    Sn
    0.07
     cached
    0.07
    כ
    0.06
    ŵ
    0.06
    情况下
    0.06
    Several
    0.06
    这种情况
    0.06
    Activations Density 0.001%

    No Known Activations