Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 88162
    Prev
    Next
    INDEX
    Explanations

    more

    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
    晚会
    -0.08
     kannst
    -0.07
    โฆษ
    -0.07
     Speaking
    -0.07
    	sh
    -0.07
     promoters
    -0.07
    崇高
    -0.07
     Snapchat
    -0.07
     различных
    -0.07
    Chat
    -0.07
    POSITIVE LOGITS
    _PUR
    0.07
     nowhere
    0.07
     مدى
    0.07
    不够
    0.07
    фф
    0.07
    ologically
    0.07
    水泥
    0.07
    acial
    0.07
     uranium
    0.07
    tał
    0.07
    Activations Density 0.050%

    No Known Activations