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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 48840
    Prev
    Next
    INDEX
    Explanations

    Also known as

    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
    Pieces
    -0.08
    /tool
    -0.07
     evidenced
    -0.07
    ▣
    -0.07
    甾
    -0.07
    ulings
    -0.06
    ateful
    -0.06
     numero
    -0.06
    	files
    -0.06
    原件
    -0.06
    POSITIVE LOGITS
     carrera
    0.07
     }}}
    0.07
     DI
    0.07
    );}
    0.07
    좐
    0.07
     RED
    0.07
    ')}}"
    0.07
    사는
    0.07
     reflexivity
    0.07
     Gerald
    0.07
    Activations Density 0.024%

    No Known Activations