© 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. 71838
    Prev
    Next
    INDEX
    Explanations

    emotional

    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
    men
    -0.07
    "';↵
    -0.07
    צפה
    -0.07
    걜
    -0.06
     "}\
    -0.06
     мам
    -0.06
    $
↵
    -0.06
    "If
    -0.06
    "People
    -0.06
    assy
    -0.06
    POSITIVE LOGITS
    .inverse
    0.08
    (cols
    0.08
    Closing
    0.07
    -red
    0.07
    _sha
    0.07
    PLIT
    0.07
    \Bridge
    0.07
     GitHub
    0.07
     orange
    0.07
    _PROXY
    0.07
    Activations Density 0.022%

    No Known Activations