Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 88467
    Prev
    Next
    INDEX
    Explanations

    questions

    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
     miesięcy
    -0.07
     annoy
    -0.07
    	atomic
    -0.07
    Translations
    -0.07
    施行
    -0.07
    solid
    -0.06
    ורג
    -0.06
    	constructor
    -0.06
     descricao
    -0.06
    发挥了
    -0.06
    POSITIVE LOGITS
     rub
    0.07
     Criterion
    0.07
     Cert
    0.07
    _med
    0.07
    ")
    0.06
     fra
    0.06
     מע
    0.06
    cheme
    0.06
    .detail
    0.06
    ┙
    0.06
    Activations Density 0.027%

    No Known Activations