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. 31125
    Prev
    Next
    INDEX
    Explanations

    Python code

    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
    mlink
    -0.07
     Wolfgang
    -0.07
    راض
    -0.07
     Held
    -0.07
     meanwhile
    -0.06
     cousins
    -0.06
    实物
    -0.06
    Methods
    -0.06
    ONSE
    -0.06
     наход
    -0.06
    POSITIVE LOGITS
    	cs
    0.08
     "_"
    0.07
     heavy
    0.07
    קצב
    0.07
     unle
    0.06
    .Est
    0.06
    眼部
    0.06
     gear
    0.06
    烶
    0.06
    Marca
    0.06
    Activations Density 0.089%

    No Known Activations