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. 71906
    Prev
    Next
    INDEX
    Explanations

    audio file processing

    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
    ཅ
    -0.07
    ✀
    -0.07
    🙊
    -0.07
    [child
    -0.07
    /password
    -0.06
    ☚
    -0.06
     besides
    -0.06
     STDMETHODCALLTYPE
    -0.06
    .ViewModel
    -0.06
    .Types
    -0.06
    POSITIVE LOGITS
    Labels
    0.07
    藍
    0.07
    狮
    0.06
     unst
    0.06
    Preview
    0.06
    信誉
    0.06
    iph
    0.06
    自私
    0.06
    擅自
    0.06
    稳定
    0.06
    Activations Density 0.078%

    No Known Activations