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. 11-RESID-POST-AA
    6. 25096
    Prev
    Next
    INDEX
    Explanations

    Magento

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vehicles
    -0.08
     CLOCK
    -0.07
    Tesla
    -0.07
     officer
    -0.07
    	il
    -0.07
     vbox
    -0.07
    _drive
    -0.07
     UNION
    -0.07
     loan
    -0.07
     minister
    -0.06
    POSITIVE LOGITS
    学子
    0.07
    أتي
    0.07
     radiant
    0.07
    马上就
    0.07
     nurturing
    0.06
    presence
    0.06
     appreciation
    0.06
     Feedback
    0.06
    POWER
    0.06
    iedade
    0.06
    Activations Density 0.021%

    No Known Activations