© 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. 19-RESID-POST-AA
    11. 75958
    Prev
    Next
    INDEX
    Explanations

    Explorers

    np_max-act-logits · gemini-2.0-flash
    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
     transparency
    -0.08
    밌
    -0.07
     반환
    -0.07
    手表
    -0.07
     ante
    -0.07
     comply
    -0.07
     Dont
    -0.07
    罄
    -0.06
    Bold
    -0.06
    媳妇
    -0.06
    POSITIVE LOGITS
    מינים
    0.08
    .reference
    0.08
    مواد
    0.07
    ."'
    0.07
     הבעיה
    0.07
     חברת
    0.06
     façon
    0.06
     Cro
    0.06
    _iterations
    0.06
    _Connection
    0.06
    Activations Density 0.028%

    No Known Activations