INDEX

Explanations

Code/Technical documents

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

Ground

-0.27

tfoot

-0.27

gium

-0.26

riot

-0.25

tÃł

-0.25

 Ground

-0.25

ØªÙĪØ±

-0.25

oire

-0.25

çŃĶåį·

-0.25

tÃ³

-0.24

POSITIVE LOGITS

ä¿İ

0.29

pus

0.26

åīĲ

0.25

 lÃ²ng

0.25

 transplantation

0.24

ç¬Ī

0.24

è¡°

0.24

aste

0.24

ipes

0.24

Nam

0.24

Activations Density 0.111%

Code/Technical documents

No Comments

No Known Activations