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. 36458
    Prev
    Next
    INDEX
    Explanations

    attention spans, media

    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
     transformers
    -0.07
     Download
    -0.07
    _login
    -0.07
    (dd
    -0.07
    问责
    -0.06
    ډ
    -0.06
    联络
    -0.06
    大战
    -0.06
    鲗
    -0.06
     Curse
    -0.06
    POSITIVE LOGITS
     сочета
    0.08
    \:
    0.07
     cob
    0.07
    窨
    0.07
    比较简单
    0.07
     oran
    0.06
    adaptive
    0.06
    🏔
    0.06
    ote
    0.06
     하나
    0.06
    Activations Density 0.021%

    No Known Activations