© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29786
    Prev
    Next
    INDEX
    Explanations

    nanoparticles

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LT
    -0.08
    	Mat
    -0.07
    -_
    -0.07
     Ratings
    -0.07
     Mat
    -0.07
    网格
    -0.06
     Guidance
    -0.06
     catalyst
    -0.06
    generate
    -0.06
     medicine
    -0.06
    POSITIVE LOGITS
    ulous
    0.08
     גיל
    0.07
    .getDrawable
    0.07
    缤纷
    0.07
    会影响到
    0.07
    .chat
    0.07
    	box
    0.07
     ücretsiz
    0.07
    วาง
    0.07
    	Logger
    0.06
    Activations Density 0.036%

    No Known Activations