INDEX

Explanations

legal cases

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

æ°ı

-0.35

Jr

-0.31

çĪ·çĪ·

-0.28

-Smith

-0.27

LR

-0.26

cker

-0.26

ç¬¬ä¸īä¸ª

-0.26

 Brothers

-0.25

Sr

-0.25

.Unity

-0.25

POSITIVE LOGITS

erate

0.25

åı¯æĥ³

0.25

gfx

0.24

 vÃ¶

0.24

haps

0.24

 recruit

0.24

iente

0.24

æĻĵ

0.23

è¯·éĢīæĭ©

0.23

ncia

0.23

Activations Density 0.260%

legal cases

No Comments

No Known Activations