© 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. 19-RESID-POST-AA
    11. 75369
    Prev
    Next
    INDEX
    Explanations

    Negative sentiment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     предприятия
    -0.07
    dealloc
    -0.07
     consumer
    -0.07
     nets
    -0.07
    (domain
    -0.06
     ctl
    -0.06
    破门
    -0.06
    碓
    -0.06
     worker
    -0.06
    .textField
    -0.06
    POSITIVE LOGITS
     suốt
    0.08
    中华民族
    0.07
    誓
    0.07
    虐待
    0.07
    绚
    0.06
    不清楚
    0.06
    偃
    0.06
    blockquote
    0.06
     summary
    0.06
    รอ
    0.06
    Activations Density 0.191%

    No Known Activations