INDEX

Explanations

Citations

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

ery

-0.31

 Concept

-0.27

Concept

-0.26

eh

-0.26

concept

-0.25

ilyn

-0.25

èĩªçĦ¶

-0.25

erv

-0.25

å·¥ä½ľå²Ĺä½į

-0.25

umi

-0.24

POSITIVE LOGITS

InstanceState

0.27

programs

0.26

.appspot

0.25

çľŁåģĩ

0.25

edException

0.24

èĢ½

0.24

LC

0.24

å¾·èĤ²

0.24

Lat

0.23

Lat

0.23

Activations Density 0.015%

Citations

No Comments

No Known Activations