Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 48528
    Prev
    Next
    INDEX
    Explanations

    URL/header/string

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iletişim
    -0.07
     sı
    -0.06
    WithPath
    -0.06
     dévelop
    -0.06
    -Javadoc
    -0.06
     uuid
    -0.06
     Edmund
    -0.06
    开支
    -0.06
     đào
    -0.06
    *num
    -0.06
    POSITIVE LOGITS
    USTER
    0.07
    amos
    0.07
     Sensor
    0.07
    zones
    0.07
    scan
    0.07
     Doesn
    0.07
    useum
    0.07
    agan
    0.07
     Dates
    0.07
     eliminating
    0.07
    Activations Density 0.016%

    No Known Activations