© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 123370
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
    Scalars
    -0.07
    (Code
    -0.07
    硫酸
    -0.06
    rx
    -0.06
     River
    -0.06
    Wik
    -0.06
     tim
    -0.06
    -heading
    -0.06
    -compose
    -0.06
    Pipe
    -0.06
    POSITIVE LOGITS
     sensory
    0.07
    歆
    0.07
    влекательн
    0.07
     Programs
    0.06
    娛樂
    0.06
    ⼆
    0.06
    ologne
    0.06
    ibbean
    0.06
     Dancing
    0.06
    orea
    0.06
    Activations Density 0.004%

    No Known Activations