INDEX

Explanations

and

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

åįĬå¤©

-0.26

MAP

-0.26

etas

-0.26

KP

-0.26

 incub

-0.26

EP

-0.25

_CONN

-0.25

MAP

-0.24

ç§ĥ

-0.24

_MAXIMUM

-0.24

POSITIVE LOGITS

 pathMatch

0.28

illi

0.28

 operand

0.26

quier

0.25

ULL

0.25

ull

0.25

ivid

0.25

fdc

0.25

ylv

0.25

<UnityEngine

0.25

Activations Density 0.086%

and

No Comments

No Known Activations