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. 7086
    Prev
    Next
    INDEX
    Explanations

    9

    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
    xdc
    -0.08
     tàu
    -0.07
     Austin
    -0.07
    琛
    -0.07
     Jesus
    -0.07
     Rudy
    -0.07
     ios
    -0.06
    或許
    -0.06
     себе
    -0.06
     vrai
    -0.06
    POSITIVE LOGITS
    LocalizedString
    0.07
    .createStatement
    0.07
    Türkiye
    0.07
    	UFUNCTION
    0.07
    .Yellow
    0.07
     Geile
    0.06
    opens
    0.06
    各个
    0.06
    占地面积
    0.06
     Rolling
    0.06
    Activations Density 0.013%

    No Known Activations