© 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. 85634
    Prev
    Next
    INDEX
    Explanations

    fix

    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
    媒
    -0.07
    ientras
    -0.07
    诨
    -0.07
    (Product
    -0.07
    ried
    -0.06
    𝗖
    -0.06
    下面就
    -0.06
    微博
    -0.06
    aneously
    -0.06
     hw
    -0.06
    POSITIVE LOGITS
    jur
    0.07
     Chrysler
    0.07
    SOR
    0.07
    checksum
    0.07
    max
    0.07
    iyor
    0.07
    zug
    0.07
    �
    0.07
    ski
    0.07
    市の
    0.07
    Activations Density 0.007%

    No Known Activations