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. 36236
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    菟
    -0.08
    ụ
    -0.07
    放宽
    -0.07
     Bet
    -0.07
     Transactions
    -0.07
     lodash
    -0.07
     rabbits
    -0.07
    <Box
    -0.07
    Flight
    -0.07
    -tax
    -0.07
    POSITIVE LOGITS
    멂
    0.06
    젱
    0.06
     effic
    0.06
     getString
    0.06
     herein
    0.06
     Именно
    0.06
    Ң
    0.06
     Đi
    0.06
     process
    0.06
     beneath
    0.06
    Activations Density 0.002%

    No Known Activations