© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75995
    Prev
    Next
    INDEX
    Explanations

    за

    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
     Hữu
    -0.07
     Molly
    -0.07
    ทรา
    -0.07
    (features
    -0.07
    平
    -0.07
     Lost
    -0.06
    ocus
    -0.06
     التط
    -0.06
     유
    -0.06
     Cong
    -0.06
    POSITIVE LOGITS
     replacement
    0.08
     בשל
    0.07
     concatenated
    0.07
    .argmax
    0.07
    ERCHANTABILITY
    0.07
     за
    0.07
    מסעד
    0.07
     xnxx
    0.07
    probante
    0.07
    struments
    0.07
    Activations Density 0.024%

    No Known Activations