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. 19-RESID-POST-AA
    6. 87755
    Prev
    Next
    INDEX
    Explanations

    to

    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
    	is
    -0.07
    不服
    -0.07
    .receive
    -0.07
    劓
    -0.07
    шки
    -0.07
    ています
    -0.07
     sucesso
    -0.07
    来看看
    -0.07
     usa
    -0.07
    .unit
    -0.07
    POSITIVE LOGITS
    �
    0.07
     INTERVAL
    0.07
     Appears
    0.06
    جير
    0.06
     comforting
    0.06
     Gy
    0.06
    .PictureBoxSizeMode
    0.06
    劣
    0.06
    وض
    0.06
     Phot
    0.06
    Activations Density 0.028%

    No Known Activations