© 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. 84886
    Prev
    Next
    INDEX
    Explanations

    Period token

    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
    底蕴
    -0.07
    😌
    -0.07
    _basename
    -0.07
    NotEmpty
    -0.07
    探寻
    -0.07
    综合利用
    -0.07
     LT
    -0.06
    韵
    -0.06
    ="<?=
    -0.06
    uctose
    -0.06
    POSITIVE LOGITS
    潲
    0.08
    뉼
    0.07
    Ⱀ
    0.07
    谔
    0.07
    ается
    0.07
    дают
    0.07
     leveled
    0.07
     Toro
    0.07
    겪
    0.07
     CPUs
    0.07
    Activations Density 0.002%

    No Known Activations