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. 72414
    Prev
    Next
    INDEX
    Explanations

    Comparing similar items

    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
    箦
    -0.08
     vertical
    -0.07
    あった
    -0.07
    רגש
    -0.07
    Seven
    -0.07
    nant
    -0.07
    remaining
    -0.06
    erez
    -0.06
     JNIEnv
    -0.06
    캤
    -0.06
    POSITIVE LOGITS
    hari
    0.07
    张家界
    0.07
    /she
    0.07
    сл
    0.07
    oug
    0.06
    spec
    0.06
    mayacağı
    0.06
    _Open
    0.06
     GLFW
    0.06
     copyrighted
    0.06
    Activations Density 0.060%

    No Known Activations