INDEX

Explanations

had

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 round

-0.28

<![

-0.27

hone

-0.27

èģļçĦ¦

-0.27

act

-0.26

è¡£

-0.25

 tháºŃp

-0.25

æłĩæĿĨ

-0.24

éļ¾

-0.24

åĵ¨

-0.24

POSITIVE LOGITS

utter

0.27

 ÑģÐºÐ°Ñĩ

0.26

Ð¾ÑĤÐ¾ÑĢ

0.25

_LIBRARY

0.25

plementation

0.25

#{@

0.25

 undergoing

0.25

 undergo

0.25

æķ¬

0.25

ialect

0.25

Activations Density 0.001%

had

No Comments

No Known Activations