INDEX

Explanations

computer code

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

dev

-0.28

.by

-0.28

åĲĮçĽŁ

-0.26

by

-0.25

PLAN

-0.25

æĥħ

-0.25

è¶Ĭ

-0.25

dev

-0.25

åĸ§

-0.24

rel

-0.24

POSITIVE LOGITS

%%%%

0.28

umbo

0.26

ularity

0.26

GINE

0.25

ê¸Īìľµ

0.25

ifter

0.24

æ¯³

0.24

 financier

0.24

 Morr

0.24

ital

0.24

Activations Density 0.013%

computer code

No Comments

No Known Activations