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. 19-RESID-POST-AA
    6. 48484
    Prev
    Next
    INDEX
    Explanations

    Code logs

    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
     oasis
    -0.07
     다음
    -0.06
    maf
    -0.06
    once
    -0.06
    antaged
    -0.06
    阅读
    -0.06
     insure
    -0.06
    牛奶
    -0.06
     bif
    -0.06
    .seed
    -0.06
    POSITIVE LOGITS
    	
    0.08
     './../../
    0.07
    急速
    0.07
    .PropTypes
    0.07
     ammunition
    0.07
    acht
    0.07
    ᴛ
    0.07
     astro
    0.06
    一
    0.06
       
    0.06
    Activations Density 0.004%

    No Known Activations