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. 88410
    Prev
    Next
    INDEX
    Explanations

    desire

    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
     Toastr
    -0.08
     altro
    -0.07
     letz
    -0.07
    eto
    -0.07
    _ext
    -0.07
    억
    -0.07
     يوجد
    -0.07
     Marsh
    -0.06
     immune
    -0.06
    _unc
    -0.06
    POSITIVE LOGITS
    坚韧
    0.08
    (depend
    0.07
     desire
    0.07
    דל
    0.07
     users
    0.07
     
    0.07
    skill
    0.07
     intent
    0.06
     who
    0.06
    痴迷
    0.06
    Activations Density 0.012%

    No Known Activations