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. 19-RESID-POST-AA
    6. 71982
    Prev
    Next
    INDEX
    Explanations

    say "0"

    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
    降低了
    -0.07
          	
    -0.07
    링
    -0.06
     adding
    -0.06
    ât
    -0.06
     cooling
    -0.06
     Texans
    -0.06
    /no
    -0.06
    icare
    -0.06
    arking
    -0.06
    POSITIVE LOGITS
     соврем
    0.06
    StartupScript
    0.06
    สวม
    0.06
    _dest
    0.06
    emat
    0.06
    duk
    0.06
     Obj
    0.06
    CppCodeGen
    0.06
     Globals
    0.06
    analysis
    0.06
    Activations Density 0.008%

    No Known Activations