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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 75689
    Prev
    Next
    INDEX
    Explanations

    player

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVER
    -0.08
    (errors
    -0.07
     Manor
    -0.07
    强烈
    -0.07
    ulg
    -0.07
     manos
    -0.07
    ا�
    -0.07
    埒
    -0.06
    -eyed
    -0.06
    ection
    -0.06
    POSITIVE LOGITS
    [data
    0.07
    `;↵
    0.07
     בלי
    0.07
    boats
    0.06
     الإسرائيل
    0.06
    .module
    0.06
    patches
    0.06
    ﮁ
    0.06
    		               
    0.06
     REGION
    0.06
    Activations Density 0.023%

    No Known Activations