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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 939
    Prev
    Next
    INDEX
    Explanations

    Module

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	fclose
    -0.08
    宋代
    -0.07
    数据显示
    -0.07
     filter
    -0.07
     Gaussian
    -0.07
    -stock
    -0.07
    lescope
    -0.06
    ']).
    -0.06
    uitable
    -0.06
     competition
    -0.06
    POSITIVE LOGITS
    ใจ
    0.07
     adversary
    0.07
    红豆
    0.07
    🙍
    0.07
    otine
    0.07
    肌肉
    0.07
    (()
    0.07
     overcoming
    0.06
    nivel
    0.06
    يد
    0.06
    Activations Density 0.000%

    No Known Activations