© 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. 42554
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
     Crud
    -0.07
     Run
    -0.07
    뵌
    -0.07
    Dev
    -0.07
    洑
    -0.07
     Mu
    -0.07
     Spe
    -0.07
     Printer
    -0.07
     Mata
    -0.06
    ffffff
    -0.06
    POSITIVE LOGITS
    ٶ
    0.07
    amenti
    0.07
    icionar
    0.07
     brib
    0.07
    /tiny
    0.07
     абсолют
    0.07
    褒
    0.06
    引用日期
    0.06
    تقييم
    0.06
    🧘
    0.06
    Activations Density 0.024%

    No Known Activations