© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73731
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Müslü
    -0.08
     umieję
    -0.07
    anuts
    -0.06
    imi
    -0.06
     살
    -0.06
    _OBS
    -0.06
     Community
    -0.06
     pandas
    -0.06
    씐
    -0.06
    統
    -0.06
    POSITIVE LOGITS
     touch
    0.07
     hugged
    0.07
    (tab
    0.07
    dating
    0.07
    巨星
    0.07
    靠
    0.07
     ○
    0.07
    ацию
    0.07
     endforeach
    0.06
    ấp
    0.06
    Activations Density 0.007%

    No Known Activations