INDEX

Explanations

Unstructured text 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç´ĭ

-0.27

preserve

-0.26

wig

-0.26

iew

-0.25

çļĦä¼ĺåĬ¿

-0.25

 preservation

-0.25

 preserve

-0.25

.heading

-0.24

IEW

-0.24

nex

-0.24

POSITIVE LOGITS

ç§¯æ°´

0.32

å¹³è¡¡

0.30

tracts

0.29

 PublicKey

0.29

 robin

0.28

POSIT

0.27

okit

0.27

 balance

0.26

 balances

0.26

_relations

0.25

Activations Density 0.359%

Unstructured text snippets

No Comments

No Known Activations