INDEX

Explanations

Carbon

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

rab

-0.28

cript

-0.27

ebra

-0.27

Psych

-0.27

æķ´é½Ĳ

-0.26

-0.25

Echo

-0.25

-0.24

ãĥ¥

-0.24

 Abyss

-0.24

POSITIVE LOGITS

SWG

0.28

ÑĳÑĢ

0.27

 Disposable

0.25

(Mod

0.25

 setSearch

0.24

.Dispose

0.24

 discharge

0.24

coal

0.24

carousel

0.23

-medium

0.23

Activations Density 0.006%

Carbon

No Comments

No Known Activations