© 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. 15-RESID-POST-AA
    11. 18841
    Prev
    Next
    INDEX
    Explanations

    auxiliary 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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    wei
    -0.07
    ᮠ
    -0.07
     sublist
    -0.07
    	canvas
    -0.07
    arena
    -0.07
    ι
    -0.07
    parseInt
    -0.07
    (--
    -0.07
    authenticate
    -0.07
    inati
    -0.07
    POSITIVE LOGITS
     SSP
    0.07
    doch
    0.07
     FULL
    0.07
    各
    0.07
    탶
    0.07
    _SUR
    0.06
     Ottoman
    0.06
     gymn
    0.06
     Förder
    0.06
     본
    0.06
    Activations Density 0.068%

    No Known Activations