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. 2755
    Prev
    Next
    INDEX
    Explanations

    specific

    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
    .clip
    -0.08
    嘭
    -0.07
    ppv
    -0.07
     typingsSlinky
    -0.07
    INCLUDING
    -0.07
    /pm
    -0.06
    enqueue
    -0.06
    tri
    -0.06
    .box
    -0.06
     ALTER
    -0.06
    POSITIVE LOGITS
     '').
    0.09
    iras
    0.07
     jue
    0.07
     version
    0.07
    工作经验
    0.07
     consistently
    0.07
    沭
    0.07
    FileSystem
    0.07
    噪音
    0.07
    .codehaus
    0.07
    Activations Density 0.004%

    No Known Activations