INDEX

Explanations

's

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

äºĭä¸ļåıĳå±ķ

-0.27

éļĻ

-0.26

çĽ¸éĤ»

-0.26

 Burr

-0.25

statt

-0.25

 Overall

-0.25

 backstory

-0.25

Overall

-0.25

 hail

-0.24

çĸĳä¼¼

-0.24

POSITIVE LOGITS

udos

0.26

upa

0.25

:new

0.25

ä»¥èĩ³äºİ

0.24

egot

0.24

abric

0.24

grades

0.24

rita

0.24

 billions

0.23

oma

0.23

Activations Density 0.935%

's

No Comments

No Known Activations