Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 23-RESID-POST-AA
    6. 424
    Prev
    Next
    INDEX
    Explanations

    wiki-like collaborative text

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anyhow
    -0.07
     celery
    -0.07
    -align
    -0.07
    quin
    -0.07
    여
    -0.07
    RelativeLayout
    -0.07
     тогда
    -0.06
    ǔ
    -0.06
    _PREFIX
    -0.06
    clare
    -0.06
    POSITIVE LOGITS
     '>'
    0.07
     eventdata
    0.07
    غال
    0.07
    _pages
    0.06
    议
    0.06
     booths
    0.06
    cb
    0.06
    ⨀
    0.06
    Great
    0.06
    ┠
    0.06
    Activations Density 0.000%

    No Known Activations