INDEX

Explanations

expressing a contrast

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

ed

-0.28

 trá»įng

-0.26

Ð´Ð°Ð»

-0.26

sequences

-0.26

èĥĮåĲİ

-0.25

ets

-0.25

éŀį

-0.25

 itself

-0.24

 retr

-0.24

POSITIVE LOGITS

 instit

0.28

åį¤

0.27

æ¦ľ

0.27

æ¯ĴæĢ§

0.26

å¸½

0.26

(Sub

0.26

ENCIL

0.26

Ã³rio

0.25

 componentWillUnmount

0.25

 Liga

0.25

Activations Density 0.028%

expressing a contrast

No Comments

No Known Activations