© 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. 19-RESID-POST-AA
    11. 8204
    Prev
    Next
    INDEX
    Explanations

    code

    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
    抑え
    -0.07
    ぇ
    -0.07
    أخلاق
    -0.07
    -olds
    -0.07
    欧美
    -0.07
     Maritime
    -0.07
     haber
    -0.06
    小游戏
    -0.06
     masters
    -0.06
    Labor
    -0.06
    POSITIVE LOGITS
     Jim
    0.08
    _BAND
    0.07
    大唐
    0.06
     flag
    0.06
    /bus
    0.06
     dispon
    0.06
    submenu
    0.06
     Chevron
    0.06
    trip
    0.06
    zn
    0.06
    Activations Density 0.028%

    No Known Activations