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. 130888
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Buf
    -0.08
    Enum
    -0.08
    ========
    -0.07
    حديث
    -0.07
     Buddy
    -0.07
    	try
    -0.07
     favor
    -0.07
     arrow
    -0.07
    _enum
    -0.07
     synonym
    -0.06
    POSITIVE LOGITS
     lesbi
    0.09
     Cra
    0.08
     pods
    0.08
     usernames
    0.07
     @@↵
    0.07
    '));
    ↵
    0.07
    ڊ
    0.07
    InputLabel
    0.07
    *>&
    0.07
    𬍤
    0.07
    Activations Density 0.008%

    No Known Activations