© 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. 75646
    Prev
    Next
    INDEX
    Explanations

    Court documents

    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
    最佳
    -0.07
    voke
    -0.07
    作者所有
    -0.07
     resolutions
    -0.07
    大家都在
    -0.07
    祏
    -0.07
    ﺆ
    -0.07
    铕
    -0.07
     babes
    -0.06
    ﷽
    -0.06
    POSITIVE LOGITS
     Gio
    0.07
     NW
    0.07
    =mysql
    0.07
    供电公司
    0.06
     hallway
    0.06
     Paran
    0.06
     seemed
    0.06
     Git
    0.06
    غي
    0.06
    .net
    0.06
    Activations Density 0.000%

    No Known Activations