INDEX

Explanations

-induced

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸įä»£è¡¨

-0.29

èµĦåĬ©

-0.27

åľºæĻ¯

-0.27

 scene

-0.26

bid

-0.26

åĽ´

-0.25

è¿Ľåľº

-0.25

 Äĳá»ģ

-0.25

è¡Įäºº

-0.25

bid

-0.25

POSITIVE LOGITS

uel

0.28

ippy

0.27

ç´¯äºĨ

0.26

åĩºåı£

0.26

 Slee

0.25

createQuery

0.25

æĪĺå½¹

0.25

ç²¾å½©çļĦ

0.25

singleton

0.25

loit

0.25

Activations Density 0.007%

-induced

No Comments

No Known Activations