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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24541
    Prev
    Next
    INDEX
    Explanations

    Repeated characters

    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
     Coke
    -0.08
    𝑒
    -0.07
    alc
    -0.07
     Shake
    -0.07
    )c
    -0.07
    ahl
    -0.07
    òn
    -0.07
     Extend
    -0.07
     Ale
    -0.07
    mute
    -0.07
    POSITIVE LOGITS
    Ό
    0.08
    ؿ
    0.07
     presup
    0.06
    ум
    0.06
    [:,:
    0.06
     ResultSet
    0.06
    בות
    0.06
    归属
    0.06
    ゴール
    0.06
     downtime
    0.06
    Activations Density 0.006%

    No Known Activations