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. 6855
    Prev
    Next
    INDEX
    Explanations

    programming posts

    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
     Startup
    -0.07
    𝐀
    -0.07
     Diễn
    -0.07
     زيادة
    -0.07
     weakening
    -0.07
    .findOne
    -0.07
     Как
    -0.07
    主导
    -0.06
     федеральн
    -0.06
     Existing
    -0.06
    POSITIVE LOGITS
    Mt
    0.08
    פטר
    0.08
    ➲
    0.07
     crypt
    0.07
    (ra
    0.07
    /min
    0.06
    机型
    0.06
    /task
    0.06
     ver
    0.06
    lat
    0.06
    Activations Density 0.052%

    No Known Activations