© 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. 130187
    Prev
    Next
    INDEX
    Explanations

    perfume descriptions

    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
    CONDS
    -0.07
     hen
    -0.07
    wie
    -0.07
     werde
    -0.07
     kak
    -0.07
    ンド
    -0.07
    writes
    -0.07
    ("");
↵
    -0.06
     Yok
    -0.06
     المصر
    -0.06
    POSITIVE LOGITS
    滋味
    0.09
     adolescence
    0.08
    _RESET
    0.08
     terse
    0.07
    semi
    0.07
     enforced
    0.07
     subt
    0.07
    comm
    0.07
     reminis
    0.07
    自私
    0.07
    Activations Density 0.022%

    No Known Activations