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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 71782
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     minds
    -0.07
     modern
    -0.07
     rud
    -0.06
     art
    -0.06
     הפועל
    -0.06
    蛊
    -0.06
    碓
    -0.06
    简便
    -0.06
    _upper
    -0.06
     germ
    -0.06
    POSITIVE LOGITS
    losures
    0.07
    ]};↵
    0.07
     --------------------
    0.07
     consultations
    0.07
    _TR
    0.07
    --------------------
    0.07
    زين
    0.07
    ustr
    0.07
    .characters
    0.07
    -processing
    0.06
    Activations Density 0.023%

    No Known Activations