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. 88337
    Prev
    Next
    INDEX
    Explanations

    Could not find another pattern

    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
     Icelandic
    -0.07
    还有什么
    -0.07
    傧
    -0.07
     grantResults
    -0.07
    ny
    -0.07
     Neural
    -0.07
     กรกฎาคม
    -0.07
    奇怪
    -0.07
     بنسبة
    -0.07
    升值
    -0.06
    POSITIVE LOGITS
     UObject
    0.07
    After
    0.07
    末
    0.07
     critique
    0.07
     upro
    0.07
    _playlist
    0.07
    rush
    0.06
     spot
    0.06
    .limit
    0.06
    無しさん
    0.06
    Activations Density 0.001%

    No Known Activations