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. 7197
    Prev
    Next
    INDEX
    Explanations

    tariff codes

    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
    =find
    -0.08
     veniam
    -0.07
    ẵ
    -0.07
     gratis
    -0.06
    之權利
    -0.06
    _xml
    -0.06
    Service
    -0.06
    ﻲ
    -0.06
     직
    -0.06
    ManagedObjectContext
    -0.06
    POSITIVE LOGITS
    多年前
    0.08
    istringstream
    0.07
     purchaser
    0.07
    开门
    0.07
    ref
    0.07
    	timer
    0.07
    rename
    0.07
    andelier
    0.07
     multiples
    0.07
    แตก
    0.06
    Activations Density 0.011%

    No Known Activations