INDEX

Explanations

book

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

ep

-0.30

Dat

-0.26

bik

-0.26

éģĩéļ¾

-0.26

datable

-0.26

etch

-0.25

AV

-0.24

 grand

-0.24

enn

-0.24

big

-0.24

POSITIVE LOGITS

oni

0.28

ections

0.25

 Newest

0.24

 ConfigurationManager

0.23

 queues

0.23

 addObject

0.23

è²Į

0.23

 momentarily

0.23

Coh

0.23

éĴŁ

0.23

Activations Density 0.013%

book

No Comments

No Known Activations