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. 59499
    Prev
    Next
    INDEX
    Explanations

    Events and staffing

    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
     Flam
    -0.08
    ⇓
    -0.07
     LOS
    -0.07
     lien
    -0.07
    ellido
    -0.07
     suffers
    -0.07
    擅长
    -0.07
    税务总局
    -0.07
    _GenericClass
    -0.07
    ฃ
    -0.06
    POSITIVE LOGITS
    redit
    0.08
    reset
    0.08
    大道
    0.07
     pwm
    0.07
    .reset
    0.07
     reset
    0.07
    _parts
    0.07
     equal
    0.07
    .variable
    0.07
     resets
    0.07
    Activations Density 0.170%

    No Known Activations