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. 27-RESID-POST-AA
    6. 130994
    Prev
    Next
    INDEX
    Explanations

    Н

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sebuah
    -0.08
    atorial
    -0.08
    INATION
    -0.07
     неск
    -0.07
    圣诞
    -0.07
     denies
    -0.07
     CGRect
    -0.07
     stormed
    -0.07
    瞧
    -0.06
     ngOnDestroy
    -0.06
    POSITIVE LOGITS
    遇到了
    0.09
    /controller
    0.07
     Cunningham
    0.07
    Sou
    0.07
     phoenix
    0.07
    /L
    0.07
    路况
    0.07
     unexpectedly
    0.06
     cri
    0.06
    Formula
    0.06
    Activations Density 0.002%

    No Known Activations