© 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. 11-RESID-POST-AA
    11. 85272
    Prev
    Next
    INDEX
    Explanations

    olympic games

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _vertical
    -0.09
    _seed
    -0.07
    魔法师
    -0.07
    品种
    -0.07
     plaster
    -0.06
    schlä
    -0.06
     pigs
    -0.06
     silenced
    -0.06
    apo
    -0.06
    活泼
    -0.06
    POSITIVE LOGITS
     авто
    0.07
    UpdatedAt
    0.07
    担保
    0.07
    坐下
    0.07
     Beaut
    0.07
     مشيرا
    0.06
     futures
    0.06
    TRUE
    0.06
     aforementioned
    0.06
     OSS
    0.06
    Activations Density 0.071%

    No Known Activations