INDEX

Explanations

ai and code snippets

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

ivities

-0.25

Spoiler

-0.25

identification

-0.25

 identification

-0.25

Identification

-0.24

allon

-0.24

 Peggy

-0.24

åħĪæĬĬ

-0.23

ingham

-0.23

bij

-0.23

POSITIVE LOGITS

//=

0.28

//=

0.28

.compose

0.27

.cn

0.25

 gravy

0.25

 toen

0.24

anceled

0.24

è´¡çĮ®

0.24

_cases

0.24

 lÃªn

0.23

Activations Density 0.040%

ai and code snippets

No Comments

No Known Activations