© 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. 9257
    Prev
    Next
    INDEX
    Explanations

    home

    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
    قلق
    -0.08
     Marxism
    -0.07
    -Tr
    -0.07
    -",
    -0.07
    TR
    -0.07
    高涨
    -0.07
    actively
    -0.07
     Trainer
    -0.07
    @endsection
    -0.07
     mỏi
    -0.07
    POSITIVE LOGITS
    stab
    0.08
     apresent
    0.07
     Overnight
    0.07
    설
    0.07
    ming
    0.07
    מומ
    0.06
    hte
    0.06
    -button
    0.06
     mat
    0.06
     Nab
    0.06
    Activations Density 0.004%

    No Known Activations