© 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. 7-RESID-POST-AA
    11. 76753
    Prev
    Next
    INDEX
    Explanations

    status

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pipes
    -0.08
     dành
    -0.08
     Newsp
    -0.07
    .steps
    -0.07
    亿
    -0.07
    养成
    -0.07
    教训
    -0.07
    井
    -0.07
     cities
    -0.07
     igen
    -0.07
    POSITIVE LOGITS
    belum
    0.08
     status
    0.08
    ocal
    0.08
    uncated
    0.07
     알아
    0.07
     Completion
    0.07
    (status
    0.07
     IconData
    0.07
     was
    0.07
     FAST
    0.06
    Activations Density 0.015%

    No Known Activations