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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109733
    Prev
    Next
    INDEX
    Explanations

    code related to screen dimensions

    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
    .UIManager
    -0.08
     Dann
    -0.07
     nâ
    -0.07
    fine
    -0.07
    Xml
    -0.07
    .localization
    -0.07
    IGO
    -0.07
     Marr
    -0.06
     Young
    -0.06
    Mapping
    -0.06
    POSITIVE LOGITS
    ὡ
    0.07
    hooks
    0.07
    monthly
    0.07
     confirm
    0.07
    新赛季
    0.06
     każdego
    0.06
     argument
    0.06
     inhibited
    0.06
    各種
    0.06
    UPPORTED
    0.06
    Activations Density 0.011%

    No Known Activations