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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2794
    Prev
    Next
    INDEX
    Explanations

    technical/instructional texts

    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
    滫
    -0.07
    发布时间
    -0.07
    (css
    -0.07
    とって
    -0.07
     עמוק
    -0.07
    롼
    -0.07
     competed
    -0.06
     sue
    -0.06
     streak
    -0.06
     göz
    -0.06
    POSITIVE LOGITS
    帜
    0.06
     sci
    0.06
    _socket
    0.06
    stär
    0.06
     configur
    0.06
     units
    0.06
     Lith
    0.06
    _sets
    0.06
    的事
    0.06
     GM
    0.06
    Activations Density 0.001%

    No Known Activations