© 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. 93148
    Prev
    Next
    INDEX
    Explanations

    deck

    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
    监察
    -0.07
     לבית
    -0.07
     Film
    -0.07
     Eth
    -0.07
    unknown
    -0.07
    amber
    -0.07
    KM
    -0.07
    pb
    -0.07
     Bi
    -0.07
    增至
    -0.07
    POSITIVE LOGITS
    .transform
    0.07
    륀
    0.07
     deserialize
    0.07
    (pass
    0.07
     aria
    0.06
    (success
    0.06
    	IL
    0.06
    茨
    0.06
     LOSS
    0.06
    TRANS
    0.06
    Activations Density 0.015%

    No Known Activations