Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 129487
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cribing
    -0.07
    검
    -0.07
    Ề
    -0.07
    ÜR
    -0.06
    ॲ
    -0.06
     Magnum
    -0.06
    锑
    -0.06
    ardi
    -0.06
    áo
    -0.06
    簡�
    -0.06
    POSITIVE LOGITS
    节奏
    0.07
    豪华
    0.07
    意境
    0.07
     pleasure
    0.07
    ease
    0.07
    Mike
    0.07
     Alamofire
    0.07
     humiliation
    0.07
    pixels
    0.07
    missive
    0.07
    Activations Density 0.036%

    No Known Activations