© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 30440
    Prev
    Next
    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incurred
    -0.07
    -radio
    -0.07
    וצרים
    -0.07
     gilt
    -0.07
    _mgr
    -0.06
     causes
    -0.06
    봬
    -0.06
    rodu
    -0.06
    	use
    -0.06
    iteur
    -0.06
    POSITIVE LOGITS
    (av
    0.07
        	
↵
    0.07
    挂
    0.07
    𝑃
    0.07
     beating
    0.06
    女人
    0.06
     menstrual
    0.06
    “In
    0.06
    Nintendo
    0.06
    Ṽ
    0.06
    Activations Density 0.012%

    No Known Activations