© 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. 42308
    Prev
    Next
    INDEX
    Explanations

    website browser support messages

    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
     prevail
    -0.07
    各方面
    -0.07
     наи
    -0.07
    _for
    -0.07
     Müdü
    -0.07
     Initialize
    -0.07
     libido
    -0.07
     Daw
    -0.07
     השני
    -0.07
     ха
    -0.07
    POSITIVE LOGITS
     sour
    0.07
    艳
    0.07
    صب
    0.07
    Aspect
    0.07
    ,A
    0.07
    جب
    0.06
     Spells
    0.06
    IMIZE
    0.06
    أسل
    0.06
    edges
    0.06
    Activations Density 0.096%

    No Known Activations