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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 87086
    Prev
    Next
    INDEX
    Explanations

    String concatenation and addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    혔
    -0.08
    륀
    -0.08
     đự
    -0.07
    𝐨
    -0.06
    🔮
    -0.06
     ula
    -0.06
    GU
    -0.06
     lah
    -0.06
    르
    -0.06
    unwrap
    -0.06
    POSITIVE LOGITS
    تصف
    0.08
    дол
    0.08
     Consolid
    0.07
    个别
    0.07
     Sims
    0.07
     Fighting
    0.07
    _ELEM
    0.07
    mour
    0.07
     swal
    0.07
    level
    0.07
    Activations Density 0.080%

    No Known Activations