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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 116628
    Prev
    Next
    INDEX
    Explanations

    ys

    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
    بيد
    -0.07
    论述
    -0.07
    heck
    -0.07
    #ifdef
    -0.06
    _can
    -0.06
    -threat
    -0.06
    怕
    -0.06
     bic
    -0.06
    Inter
    -0.06
    滿足
    -0.06
    POSITIVE LOGITS
    銀行
    0.08
    كات
    0.07
     personalize
    0.07
    恓
    0.07
    瘿
    0.07
    好吗
    0.07
    缲
    0.07
    的行为
    0.07
    uros
    0.07
    >*</
    0.07
    Activations Density 0.002%

    No Known Activations