© 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. 56953
    Prev
    Next
    INDEX
    Explanations

    past tense/participle verbs

    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
    Negative Logits
     Queens
    -0.08
    สะดวก
    -0.08
    Bo
    -0.08
    놨
    -0.08
     wholesome
    -0.07
    {text
    -0.07
     Strait
    -0.07
    رعاية
    -0.07
     espos
    -0.07
     Asian
    -0.07
    POSITIVE LOGITS
    .rate
    0.07
    常委会
    0.07
     ...↵↵
    0.07
    嗵
    0.07
     CONSTRAINT
    0.06
    릏
    0.06
     étape
    0.06
     testName
    0.06
    헣
    0.06
    ⏰
    0.06
    Activations Density 0.202%

    No Known Activations