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. 131011
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Regression
    -0.07
    .notifications
    -0.07
    EventData
    -0.07
    _aes
    -0.06
     startup
    -0.06
    榻
    -0.06
    炉
    -0.06
     đuổi
    -0.06
     Retrofit
    -0.06
     Meditation
    -0.06
    POSITIVE LOGITS
    과학
    0.07
     yacc
    0.07
    *w
    0.06
    _COLL
    0.06
    ἶ
    0.06
    拘
    0.06
     распрост
    0.06
    꿨
    0.06
    牺
    0.06
    쌌
    0.06
    Activations Density 0.000%

    No Known Activations