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. 15-RESID-POST-AA
    6. 27997
    Prev
    Next
    INDEX
    Explanations

    Programming descriptions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adapté
    -0.07
     הדברים
    -0.07
    قود
    -0.07
    ברה
    -0.07
    -gradient
    -0.07
     cmb
    -0.07
     Đăng
    -0.07
     BER
    -0.07
    ء
    -0.07
     nächste
    -0.07
    POSITIVE LOGITS
    ?")↵
    0.07
    หม
    0.06
    ארוח
    0.06
     pore
    0.06
     fontsize
    0.06
    ascular
    0.06
    菜
    0.06
    ATOM
    0.06
    .*
    0.06
    		
    ↵		
    ↵
    0.06
    Activations Density 0.001%

    No Known Activations