© 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. 7-RESID-POST-AA
    11. 12102
    Prev
    Next
    INDEX
    Explanations

    acs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _sz
    -0.07
    ῡ
    -0.07
    壁垒
    -0.07
    𝚎
    -0.07
    .isUser
    -0.07
     biên
    -0.07
    𝚒
    -0.06
    덬
    -0.06
    |$
    -0.06
     Zu
    -0.06
    POSITIVE LOGITS
    Charlie
    0.07
    _current
    0.07
    ducted
    0.07
    slides
    0.07
     advent
    0.07
     latest
    0.07
    vent
    0.07
     Max
    0.07
     устройства
    0.07
    last
    0.07
    Activations Density 0.010%

    No Known Activations