© 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. 22839
    Prev
    Next
    INDEX
    Explanations

    could not find any patterns, expensive

    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
    כאן
    -0.08
     Investigations
    -0.07
    洫
    -0.07
    ฏ
    -0.07
    Ӝ
    -0.06
     zipfile
    -0.06
    ᡤ
    -0.06
    Miami
    -0.06
     Tod
    -0.06
    تكنولوجيا
    -0.06
    POSITIVE LOGITS
     ret
    0.08
    收回
    0.08
     Scar
    0.07
     Kan
    0.07
     Abilities
    0.07
     а
    0.07
     Within
    0.07
     sort
    0.07
     receptors
    0.07
     ds
    0.07
    Activations Density 0.000%

    No Known Activations