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. 2805
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
     wrote
    -0.07
    .AutoComplete
    -0.07
    Ṛ
    -0.07
     Elves
    -0.07
    𒄷
    -0.07
    Ώ
    -0.07
     Lv
    -0.07
    /Search
    -0.06
     Curso
    -0.06
    Ѵ
    -0.06
    POSITIVE LOGITS
     Behind
    0.08
    最基本的
    0.08
     ()
    0.07
    臂
    0.07
     ?>"><
    0.07
    setw
    0.07
     =================================
    0.07
     LEGO
    0.07
    狠狠
    0.07
     Ergebn
    0.07
    Activations Density 0.058%

    No Known Activations