© 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. 15-RESID-POST-AA
    6. 123054
    Prev
    Next
    INDEX
    Explanations

    dominate

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngine
    -0.07
     explaining
    -0.06
    니
    -0.06
    <G
    -0.06
    长长
    -0.06
    	sem
    -0.06
    -rule
    -0.06
    圫
    -0.06
    nnen
    -0.06
     permissible
    -0.06
    POSITIVE LOGITS
     overwhelmed
    0.07
    ⁎
    0.07
    Hope
    0.07
     Funds
    0.07
     Incredible
    0.07
    GRES
    0.07
     Dee
    0.06
    杰
    0.06
     Galactic
    0.06
    基建
    0.06
    Activations Density 0.019%

    No Known Activations