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. 87916
    Prev
    Next
    INDEX
    Explanations

    found

    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
     volunt
    -0.08
    حاضر
    -0.08
     bottle
    -0.07
    馒头
    -0.07
     Lamp
    -0.07
     smells
    -0.07
    卬
    -0.07
    createUrl
    -0.07
    引领
    -0.07
    果实
    -0.07
    POSITIVE LOGITS
    >');↵↵
    0.08
     loading
    0.07
    )`↵
    0.07
    ')),↵
    0.07
    '''
    ↵
    0.07
    )")↵↵
    0.07
     sa
    0.07
    𝓫
    0.07
    `
    ↵
    0.07
    支持
    0.07
    Activations Density 0.000%

    No Known Activations