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. 24358
    Prev
    Next
    INDEX
    Explanations

    reward for hard work

    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
    唯美
    -0.08
     attraction
    -0.07
    aggio
    -0.07
    انتشار
    -0.07
     Кроме
    -0.07
     어
    -0.07
     inset
    -0.07
    いま
    -0.07
     streets
    -0.07
     velvet
    -0.07
    POSITIVE LOGITS
    	save
    0.07
     (~
    0.07
    公益
    0.07
    	server
    0.07
    fund
    0.07
     PROCESS
    0.06
    _permission
    0.06
    server
    0.06
    .plus
    0.06
    _an
    0.06
    Activations Density 0.030%

    No Known Activations