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. 23-RESID-POST-AA
    6. 130804
    Prev
    Next
    INDEX
    Explanations

    good or bad ideas

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lau
    -0.08
     vai
    -0.07
     Hu
    -0.07
     סו
    -0.07
     Kushner
    -0.07
     Kuala
    -0.07
     Vulner
    -0.06
     الفت
    -0.06
    .radians
    -0.06
     שע
    -0.06
    POSITIVE LOGITS
     mane
    0.07
    ogeneity
    0.07
    ../
    0.07
     ./
    0.07
    ומות
    0.07
    共同体
    0.07
    še
    0.07
    ображен
    0.07
    	Connection
    0.06
    erial
    0.06
    Activations Density 0.045%

    No Known Activations