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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 130567
    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
    晌
    -0.07
    扭
    -0.07
    (Expected
    -0.07
    .client
    -0.07
     amy
    -0.07
    .Collectors
    -0.07
     Customs
    -0.06
    cılar
    -0.06
    (",");↵
    -0.06
    夕
    -0.06
    POSITIVE LOGITS
     untreated
    0.07
    ''.
    0.07
    気が
    0.07
     организ
    0.07
     الشعر
    0.07
    医护人员
    0.07
    férence
    0.06
    zeichnet
    0.06
     HS
    0.06
     плат
    0.06
    Activations Density 0.025%

    No Known Activations