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. 3017
    Prev
    Next
    INDEX
    Explanations

    jQuery

    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
     científico
    -0.07
    -production
    -0.07
     obras
    -0.07
    	cb
    -0.07
     presença
    -0.07
    却是
    -0.07
    撺
    -0.07
    	properties
    -0.07
     casos
    -0.07
     neighbours
    -0.07
    POSITIVE LOGITS
     Long
    0.08
    Enlarge
    0.07
    ]</
    0.07
    uate
    0.07
    ')?></
    0.07
    少なく
    0.07
     JT
    0.07
    _blank
    0.07
     מהמע
    0.07
     },
    0.07
    Activations Density 0.001%

    No Known Activations