© 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. 40442
    Prev
    Next
    INDEX
    Explanations

    #else

    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
     stellt
    -0.08
    になっています
    -0.08
    Group
    -0.07
    ירוע
    -0.07
    برشلون
    -0.07
    となっている
    -0.07
    andra
    -0.07
     dubbed
    -0.07
     chậm
    -0.07
    .assertNotNull
    -0.07
    POSITIVE LOGITS
     Rapids
    0.08
    当事
    0.08
    >B
    0.07
    交通枢纽
    0.07
    Roboto
    0.07
    [X
    0.07
    Firebase
    0.07
     lastname
    0.07
    ffi
    0.07
     by
    0.06
    Activations Density 0.002%

    No Known Activations