© 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. 11-RESID-POST-AA
    11. 34780
    Prev
    Next
    INDEX
    Explanations

    presenting

    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
    ="<
    -0.08
    تطوير
    -0.07
    �
    -0.07
    Cpp
    -0.07
     located
    -0.07
    回避
    -0.06
     Issue
    -0.06
    enders
    -0.06
    ˚
    -0.06
    榰
    -0.06
    POSITIVE LOGITS
    eler
    0.07
    пов
    0.07
    会引起
    0.07
     gad
    0.07
     variations
    0.07
    楩
    0.07
     желез
    0.07
     Largest
    0.07
    לית
    0.07
     china
    0.07
    Activations Density 0.004%

    No Known Activations