© 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. 123303
    Prev
    Next
    INDEX
    Explanations

    negative comments

    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
    那里
    -0.07
    ''.
    -0.07
    _ib
    -0.07
    アル
    -0.07
    출
    -0.07
    宣称
    -0.07
    .cleanup
    -0.06
     trưng
    -0.06
    =[]
↵
    -0.06
     евро
    -0.06
    POSITIVE LOGITS
    ǔ
    0.07
    angled
    0.07
     sanitizer
    0.07
    王者荣耀
    0.07
    心思
    0.07
     Scotch
    0.07
    局副局长
    0.06
    angling
    0.06
    ränk
    0.06
    си
    0.06
    Activations Density 0.093%

    No Known Activations