INDEX

Explanations

Meetings and discussions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xBB

-0.27

çĴĥ

-0.25

xBC

-0.25

sap

-0.25

Kent

-0.25

åĪ©çī©

-0.24

 slips

-0.24

qed

-0.24

 reason

-0.24

.esp

-0.24

POSITIVE LOGITS

mee

0.28

 ìĤ¬ìĹħ

0.28

 session

0.28

 where

0.28

ìĤ¬ìĹħ

0.27

æľŁéĹ´

0.27

æīĵäºĨ

0.27

sym

0.27

ä¸¾åĬŀçļĦ

0.27

 Session

0.26

Activations Density 0.013%

Meetings and discussions

No Comments

No Known Activations