© 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. 24056
    Prev
    Next
    INDEX
    Explanations

    Objects

    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
    кова
    -0.07
     الفكر
    -0.07
    _pet
    -0.06
    指标
    -0.06
    cept
    -0.06
    笱
    -0.06
    扑
    -0.06
    etxt
    -0.06
     Simmons
    -0.06
     Tes
    -0.06
    POSITIVE LOGITS
     Ancient
    0.08
    During
    0.08
    =↵
    0.07
    ---↵
    0.07
    /local
    0.07
    ኍ
    0.07
     Partial
    0.07
     Session
    0.07
     요청
    0.07
    },
↵
    0.07
    Activations Density 0.001%

    No Known Activations