© 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. 123628
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS color codes

    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
    ภาวะ
    -0.09
     Settings
    -0.07
     OO
    -0.07
     tecrübe
    -0.07
    辏
    -0.07
     presente
    -0.07
    ahrung
    -0.07
    ện
    -0.07
     chế
    -0.07
    événement
    -0.07
    POSITIVE LOGITS
     fertile
    0.07
    礼物
    0.07
     preview
    0.07
     litt
    0.07
     fodder
    0.07
     автор
    0.07
     tiles
    0.07
    去掉
    0.07
    游击队
    0.07
    连云港
    0.06
    Activations Density 0.011%

    No Known Activations