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. 15-RESID-POST-AA
    6. 78004
    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_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
     декабря
    -0.08
    ificent
    -0.08
     consultant
    -0.07
    \Resource
    -0.07
    اسر
    -0.07
    _FOUND
    -0.06
    불
    -0.06
     Leicester
    -0.06
    那個
    -0.06
    .Measure
    -0.06
    POSITIVE LOGITS
    	number
    0.08
     knitting
    0.07
     למעלה
    0.07
     Coverage
    0.07
     Wiring
    0.07
     "(\<
    0.06
    Voltage
    0.06
    .keras
    0.06
    	K
    0.06
    PEED
    0.06
    Activations Density 0.003%

    No Known Activations