© 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. 69347
    Prev
    Next
    INDEX
    Explanations

    technical questions/suggestions

    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
     Where
    -0.08
    起來
    -0.07
     לט
    -0.07
     כל
    -0.07
     ],↵↵
    -0.07
     thought
    -0.07
     כפי
    -0.07
    <WebElement
    -0.07
    ثقافة
    -0.07
    /apt
    -0.07
    POSITIVE LOGITS
     horm
    0.08
    ritz
    0.07
    urret
    0.07
     revers
    0.06
    رحم
    0.06
    rompt
    0.06
    쵝
    0.06
    aset
    0.06
     significantly
    0.06
    ocations
    0.06
    Activations Density 0.198%

    No Known Activations