© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85158
    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
     iv
    -0.07
     testers
    -0.07
     mac
    -0.07
     INS
    -0.07
     메
    -0.07
    Ӣ
    -0.07
    ﲜ
    -0.07
    いち
    -0.07
    פופולרי
    -0.07
    Bush
    -0.07
    POSITIVE LOGITS
    _decor
    0.07
     registr
    0.06
     heure
    0.06
    .Alignment
    0.06
     pragma
    0.06
    	person
    0.06
    小說
    0.06
    manship
    0.06
    endid
    0.06
    composite
    0.06
    Activations Density 0.002%

    No Known Activations