© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 9741
    Prev
    Next
    INDEX
    Explanations

    Children living with relatives

    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
    Negative Logits
     Allocation
    -0.07
    湉
    -0.07
    สะ
    -0.07
     proactive
    -0.07
    FILTER
    -0.07
     Replica
    -0.07
     solicit
    -0.06
    瑅
    -0.06
    .redirect
    -0.06
     Disabled
    -0.06
    POSITIVE LOGITS
    stood
    0.07
    小编一起
    0.07
    (",")↵
    0.07
    주는
    0.07
    (generator
    0.07
    文中
    0.07
    >",↵
    0.07
    assa
    0.07
     а
    0.07
     _____
    0.06
    Activations Density 0.014%

    No Known Activations