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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 59760
    Prev
    Next
    INDEX
    Explanations

    .TimeUnit

    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
    醫生
    -0.07
    .PL
    -0.07
     oli
    -0.07
     gy
    -0.07
    生产工艺
    -0.07
     picture
    -0.07
     ++;↵
    -0.07
    腿部
    -0.07
    廣告
    -0.07
     borrow
    -0.06
    POSITIVE LOGITS
            ↵        ↵
    0.07
     Tak
    0.07
    .TimeUnit
    0.07
     Para
    0.07
     em
    0.07
    同时也是
    0.07
     climates
    0.06
    нстру
    0.06
     relaxation
    0.06
     Coun
    0.06
    Activations Density 0.000%

    No Known Activations