INDEX

Explanations

Technical descriptions and instructions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

HIP

-0.27

åŀĤ

-0.27

å¼Ĥ

-0.26

å¯¹åŃ¦çĶŁ

-0.26

æĮ¤

-0.26

è·Į

-0.25

Ã§ek

-0.24

è¹Ī

-0.24

cod

-0.24

estring

-0.23

POSITIVE LOGITS

atts

0.25

ç½Ĥ

0.24

ender

0.24

æŃ¤ç§į

0.23

 Continuing

0.23

å±ŀäºİèĩªå·±

0.23

 Recommend

0.22

andler

0.22

èĥ½åĬĽåĴĮ

0.22

 pals

0.22

Activations Density 0.001%

Technical descriptions and instructions

No Comments

No Known Activations