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. 131041
    Prev
    Next
    INDEX
    Explanations

    7

    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
    存活
    -0.08
     reclaimed
    -0.07
    olut
    -0.07
    �
    -0.07
    掉
    -0.07
    li
    -0.07
    ữu
    -0.07
     substring
    -0.07
    </
    -0.07
            
    -0.07
    POSITIVE LOGITS
    7
    0.12
     กรกฎาคม
    0.09
     July
    0.08
    7
    0.08
     يوليو
    0.08
     septembre
    0.07
    sched
    0.07
     Mend
    0.07
    _renderer
    0.07
    データ
    0.07
    Activations Density 0.305%

    No Known Activations