© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 20756
    Prev
    Next
    INDEX
    Explanations

    pc/lpc

    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
     floppy
    -0.07
    	write
    -0.07
    2
    -0.07
    ಯ
    -0.07
    力气
    -0.07
     Nietzsche
    -0.06
     Profession
    -0.06
    Instagram
    -0.06
     HIM
    -0.06
     Maver
    -0.06
    POSITIVE LOGITS
    Numer
    0.07
     חוק
    0.07
    סוג
    0.07
     Guzzle
    0.07
     emerg
    0.07
    姑
    0.07
     Pract
    0.07
    :\"
    0.07
    用工
    0.06
    portun
    0.06
    Activations Density 0.006%

    No Known Activations