© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22128
    Prev
    Next
    INDEX
    Explanations

    vacant properties and vacancies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑģебÑı
    -0.12
    halb
    -0.10
    ijo
    -0.08
    orm
    -0.08
    charged
    -0.08
    miss
    -0.08
    aceous
    -0.08
    rea
    -0.08
     Summon
    -0.08
    isle
    -0.08
    POSITIVE LOGITS
    aday
    0.11
    å·²ä¹ħçļĦ
    0.10
    rd
    0.10
    apons
    0.09
    ç§ijåѦåıijå±ķ
    0.09
     Há»Ļi
    0.08
    ademic
    0.08
    ла
    0.08
    iert
    0.08
    rate
    0.08
    Activations Density 0.018%

    No Known Activations