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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1180
    Prev
    Next
    INDEX
    Explanations

    |

    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
     дал
    -0.08
     début
    -0.07
    频道
    -0.06
     Más
    -0.06
     déc
    -0.06
     nós
    -0.06
     Hits
    -0.06
     Bas
    -0.06
     debido
    -0.06
     Cleans
    -0.06
    POSITIVE LOGITS
     компания
    0.07
    constructed
    0.07
     fraternity
    0.07
    storage
    0.07
    앎
    0.07
    贻
    0.07
    []):
    0.07
     לחוק
    0.07
     ORM
    0.07
    -sh
    0.07
    Activations Density 0.004%

    No Known Activations