INDEX

Explanations

ink

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

anders

-0.26

 clans

-0.26

env

-0.24

ETS

-0.24

 turnover

-0.24

 turnovers

-0.24

å¸Ĥåİ¿

-0.24

utors

-0.24

å¹´çĶ±

-0.24

 spoilers

-0.24

POSITIVE LOGITS

compound

0.26

åħ¶éĹ´

0.25

 Compound

0.25

åĴ½åĸī

0.25

.sym

0.25

è·¯å¾Ħ

0.24

ighted

0.24

 Jong

0.24

title

0.24

 IntPtr

0.24

Activations Density 0.014%

ink

No Comments

No Known Activations