© 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. 7-RESID-POST-AA
    11. 57208
    Prev
    Next
    INDEX
    Explanations

    in

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    祊
    -0.07
     Elizabeth
    -0.07
    🅂
    -0.07
    ﳕ
    -0.07
     Psalm
    -0.07
     تعالى
    -0.07
     HS
    -0.07
    โครงการ
    -0.07
    ʖ
    -0.07
     Torah
    -0.07
    POSITIVE LOGITS
     iff
    0.07
     đổi
    0.07
    	and
    0.07
    iffer
    0.07
    _ast
    0.07
    (sum
    0.07
    '/>
    0.07
     jusqu
    0.07
     guardian
    0.07
    	fail
    0.06
    Activations Density 0.012%

    No Known Activations