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. 24526
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    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
    ᕦ
    -0.07
     immunity
    -0.07
    幅
    -0.06
    fühl
    -0.06
    _via
    -0.06
    .ads
    -0.06
    냘
    -0.06
    孑
    -0.06
     mixed
    -0.06
     	
    -0.06
    POSITIVE LOGITS
     Bundle
    0.07
     Arte
    0.07
     변경
    0.07
     노
    0.07
     Naruto
    0.07
     שנה
    0.07
    セット
    0.07
    Creation
    0.06
     NotificationCenter
    0.06
     Obt
    0.06
    Activations Density 0.043%

    No Known Activations