© 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. 11-RESID-POST-AA
    11. 107631
    Prev
    Next
    INDEX
    Explanations

    mentions of people

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سوف
    -0.08
     Retorna
    -0.08
    晞
    -0.07
     unwilling
    -0.07
    灼
    -0.07
     voc
    -0.07
     hardly
    -0.07
     alot
    -0.07
     hike
    -0.07
    Today
    -0.06
    POSITIVE LOGITS
    就来看看
    0.08
     (+
    0.07
    �
    0.07
    anken
    0.06
    SCALL
    0.06
    .frame
    0.06
    ,eg
    0.06
    _easy
    0.06
    ™
    0.06
     behavior
    0.06
    Activations Density 0.214%

    No Known Activations