© 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. 19-RESID-POST-AA
    11. 75215
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kutje
    -0.07
     نتي
    -0.07
     dolayı
    -0.07
     대하여
    -0.07
    克斯
    -0.07
    מלח
    -0.07
     prayed
    -0.06
     харак
    -0.06
    行使
    -0.06
    	me
    -0.06
    POSITIVE LOGITS
    
    0.07
    当然是
    0.07
    早就
    0.07
    _me
    0.07
    >()↵↵
    0.07
    '></
    0.06
    PLL
    0.06
    atars
    0.06
    (st
    0.06
     **/↵
    0.06
    Activations Density 0.035%

    No Known Activations