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. 2746
    Prev
    Next
    INDEX
    Explanations

    academic publications

    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
    达成
    -0.07
    (adj
    -0.07
     RouterModule
    -0.07
    同期
    -0.07
     performing
    -0.07
     HttpStatusCode
    -0.07
    			↵			↵
    -0.07
    接触
    -0.06
    @click
    -0.06
    뻅
    -0.06
    POSITIVE LOGITS
    汉子
    0.09
     Category
    0.07
    /Z
    0.07
    主演
    0.07
    就这样
    0.07
     Babies
    0.07
    irectory
    0.06
    典范
    0.06
    straints
    0.06
    .radians
    0.06
    Activations Density 0.015%

    No Known Activations