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. 130984
    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
    Massage
    -0.08
     imperson
    -0.08
     molec
    -0.07
    的朋友
    -0.07
    كه
    -0.07
     Melanie
    -0.07
     powerless
    -0.07
    ###↵
    -0.07
    秸秆
    -0.07
    aniem
    -0.07
    POSITIVE LOGITS
    🇦
    0.07
    ブ
    0.07
    곾
    0.07
     dividing
    0.07
     Practices
    0.07
    usual
    0.06
    ={'
    0.06
     espect
    0.06
    DS
    0.06
     초기
    0.06
    Activations Density 0.140%

    No Known Activations