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. 23-RESID-POST-AA
    6. 130572
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chat
    -0.08
     completa
    -0.07
     hed
    -0.07
     criticize
    -0.07
    visualization
    -0.07
    asi
    -0.07
     exhaustion
    -0.07
    forum
    -0.07
     criticism
    -0.07
    Dimension
    -0.07
    POSITIVE LOGITS
     Diaz
    0.07
    /";↵↵
    0.07
    'E
    0.07
     paw
    0.07
     yatırım
    0.06
    EndElement
    0.06
    ኤ
    0.06
     readdir
    0.06
    DIRECTORY
    0.06
    /player
    0.06
    Activations Density 0.001%

    No Known Activations