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. 24413
    Prev
    Next
    INDEX
    Explanations

    say "th"

    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
    lesen
    -0.07
    _place
    -0.07
     wager
    -0.07
    _offsets
    -0.07
    قوم
    -0.07
    רוצה
    -0.06
    ום
    -0.06
    羔
    -0.06
    лин
    -0.06
     común
    -0.06
    POSITIVE LOGITS
    QUERY
    0.07
    ramework
    0.07
     Might
    0.07
    NET
    0.07
    @Before
    0.07
    .opt
    0.06
    antly
    0.06
    工业园区
    0.06
     CATEGORY
    0.06
    /max
    0.06
    Activations Density 0.003%

    No Known Activations