Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 36339
    Prev
    Next
    INDEX
    Explanations

    Code/Technical snippets

    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
    增持
    -0.07
     thing
    -0.07
    kar
    -0.07
    ང
    -0.07
     volatile
    -0.07
     card
    -0.06
     Mars
    -0.06
    说明书
    -0.06
    扰乱
    -0.06
    ADD
    -0.06
    POSITIVE LOGITS
    社会稳定
    0.07
     Counties
    0.07
     생산
    0.07
    現在
    0.07
    	UFUNCTION
    0.06
    Ἐ
    0.06
     Inherits
    0.06
     damages
    0.06
    ataka
    0.06
    પ
    0.06
    Activations Density 0.194%

    No Known Activations