INDEX

Explanations

text fragments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

pto

-0.31

ÑģÑĤÐ¾

-0.29

itos

-0.27

utenberg

-0.26

annis

-0.25

å©µ

-0.25

coc

-0.25

æķĪèĥ½

-0.25

zion

-0.24

rove

-0.24

POSITIVE LOGITS

TextNode

0.26

emics

0.25

UDO

0.24

Zap

0.24

-ne

0.24

(generator

0.24

 Floors

0.24

 Drama

0.24

 floors

0.23

#elif

0.23

Activations Density 0.006%

text fragments

No Comments

No Known Activations