INDEX

Explanations

and or

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nox

-0.28

Mix

-0.26

MSR

-0.25

habi

-0.25

LF

-0.25

èĨĿ

-0.24

çļĦç»ıåİĨ

-0.23

Inn

-0.23

Mix

-0.23

Fox

-0.23

POSITIVE LOGITS

 Redistributions

0.28

èĤ¢

0.28

è¸Ĭ

0.27

çĽŁ

0.27

arlo

0.27

åĳĹ

0.26

å¤§å¤ļæķ°äºº

0.25

ãģ°

0.25

ral

0.25

rote

0.24

Activations Density 0.004%

and or

No Comments

No Known Activations