INDEX

Explanations

code, math, metadata

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

thro

-0.27

isos

-0.25

ä½ĵç§¯

-0.24

 Ð¾Ð±ÑĬÐµÐ¼

-0.23

volume

-0.23

*=

-0.23

æłİ

-0.23

avage

-0.23

Ð¾ÑģÑĮ

-0.23

pitch

-0.23

POSITIVE LOGITS

 dict

0.31

-cond

0.30

 dicts

0.29

.dict

0.28

ques

0.27

ãĥ¯ãĥ³

0.27

åĩŃ

0.27

cem

0.27

ddb

0.25

xbb

0.25

Activations Density 20.910%

code, math, metadata

No Comments

No Known Activations