© 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. 15-RESID-POST-AA
    11. 123850
    Prev
    Next
    INDEX
    Explanations

    red

    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
    ’est
    -0.07
    Discover
    -0.07
     cour
    -0.07
    _co
    -0.07
    再加上
    -0.06
    上面
    -0.06
    _abs
    -0.06
    作为一种
    -0.06
    لو
    -0.06
    ורג
    -0.06
    POSITIVE LOGITS
     SS
    0.07
     lua
    0.07
     Deus
    0.07
     Lowell
    0.07
    瀱
    0.06
     Rune
    0.06
    Z
    0.06
     SSH
    0.06
    氨酸
    0.06
    nx
    0.06
    Activations Density 0.003%

    No Known Activations