© 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. 92451
    Prev
    Next
    INDEX
    Explanations

    DR/R

    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
    高中生
    -0.08
    储备
    -0.07
    .Serial
    -0.07
    .SpringApplication
    -0.07
    院校
    -0.07
    .BufferedReader
    -0.07
    🔀
    -0.07
    技术和
    -0.07
     Nom
    -0.07
       ↵    ↵
    -0.07
    POSITIVE LOGITS
    maj
    0.08
    ={[↵
    0.07
    쩻
    0.07
    Clip
    0.07
     FAILED
    0.06
     pari
    0.06
    뿐만
    0.06
    Fra
    0.06
    ense
    0.06
    nze
    0.06
    Activations Density 0.006%

    No Known Activations