© 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. 12948
    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_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
    chants
    -0.07
    hở
    -0.07
     denominator
    -0.07
    än
    -0.07
    äh
    -0.07
    宽敞
    -0.07
    isseur
    -0.07
    _PIPE
    -0.07
     cach
    -0.07
    Composer
    -0.07
    POSITIVE LOGITS
     Scheme
    0.07
    Encode
    0.07
    시키
    0.07
    [current
    0.07
    _VAL
    0.07
    برج
    0.07
     multiplication
    0.07
    ynchronize
    0.07
    ייעוץ
    0.06
    _image
    0.06
    Activations Density 0.013%

    No Known Activations