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. 11-RESID-POST-AA
    6. 75508
    Prev
    Next
    INDEX
    Explanations

    summing values

    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
     %.
    -0.08
     ähn
    -0.08
     startPoint
    -0.07
     hastalık
    -0.07
    觜
    -0.07
     לצפיה
    -0.07
    	RTLU
    -0.07
    <const
    -0.07
    蛆
    -0.07
    ถน
    -0.07
    POSITIVE LOGITS
    leon
    0.08
    -us
    0.07
    Joseph
    0.06
    received
    0.06
    	http
    0.06
     Joseph
    0.06
    emploi
    0.06
     проведения
    0.06
    ans
    0.06
    navbar
    0.06
    Activations Density 0.083%

    No Known Activations