© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 1555
    Prev
    Next
    INDEX
    Explanations

    gastr

    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
     הקוד
    -0.07
     Transport
    -0.07
    rowad
    -0.07
     conceive
    -0.07
    ',(
    -0.07
    .row
    -0.07
    Allocator
    -0.07
    -state
    -0.07
     Policy
    -0.07
     Brotherhood
    -0.06
    POSITIVE LOGITS
    обща
    0.08
    XR
    0.07
     Scar
    0.07
    ❈
    0.06
     eating
    0.06
    .disable
    0.06
    王者荣耀
    0.06
     iOS
    0.06
    roll
    0.06
    اعد
    0.06
    Activations Density 0.040%

    No Known Activations